© 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. 10-GEMMASCOPE-RES-131K
    7. 65483
    Prev
    Next
    INDEX
    Explanations

    Akbar, Krebs, ibn, Wat, おもらし

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

    The neuron fires on named‐entity tokens—proper nouns, product/model codes, acronyms, and other identifiers.

    oai_token-act-pair · o4-miniTriggered 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
    \
    -3.02
     Inglés
    -2.19
     olu
    -2.19
     comentários
    -2.16
    姈
    -2.13
    🌻
    -2.11
     используется
    -2.11
    有个
    -2.09
    芎
    -2.08
    💁
    -2.06
    POSITIVE LOGITS
    嵛
    3.38
    蓥
    2.77
    änemark
    2.64
     überprü
    2.63
     selben
    2.61
     Даже
    2.58
    得不
    2.50
     entwick
    2.48
     puede
    2.48
    or
    2.47
    Activations Density 0.448%

    No Known Activations