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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59951
    Prev
    Next
    INDEX
    Explanations

    programming lists

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

    The neuron fires strongly on occurrences of the token “list” (or “List”) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    囵
    -1.04
    ATLAS
    -1.02
     Eighteen
    -1.01
    ᖃ
    -0.99
    琯
    -0.98
    maktadır
    -0.98
     畳
    -0.98
    を買う
    -0.96
    fleet
    -0.96
    blowing
    -0.96
    POSITIVE LOGITS
    ened
    1.59
    ings
    1.28
     '
    1.21
    ner
    1.21
    as
    1.20
    ....
    1.18
    :"
    1.16
    '
    1.10
    ine
    1.07
    ''
    1.06
    Activations Density 0.087%

    No Known Activations