© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14284
    Prev
    Next
    INDEX
    Explanations

    skilled craftsman with the chops necessary

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron consistently fires on any occurrence of the letter sequence “chop” (in words like “chops,” “Chopin,” “chophoresis,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words containing the “chop” morpheme, whether used idiomatically for skill, as part of proper nouns, or embedded within longer technical terms.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "chop" or variations of it, particularly in names like "Chopin" or compound words like "chopsticks" and "chops" (as in skill/ability).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -3.27
    豋
    -2.70
    ஂ
    -2.66
    s
    -2.48
    >
    -2.42
    梣
    -2.27
     bianca
    -2.20
    疍
    -2.19
     RSITY
    -2.16
    垕
    -2.13
    POSITIVE LOGITS
    ſu
    2.34
     çeşitli
    2.27
     scramble
    2.22
     happenings
    2.20
     reduzieren
    2.16
    𐬹
    2.16
     Ин
    2.14
     ........
    2.14
     şi
    2.13
     cringe
    2.13
    Activations Density 0.002%

    No Known Activations