© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45426
    Prev
    Next
    INDEX
    Explanations

    abbreviations and identifiers

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

    abbreviations and identifiers like "Ip", "Args", and "Tmp" in programming and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on code‐style identifiers or variable/class names that begin with an uppercase letter (e.g. “Ids”, “CityIds”, “Args”), effectively spotting capitalized code tokens.

    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
    ?
    -3.17
    ).
    -2.67
    !
    -2.53
    纜
    -2.31
     邊
    -2.31
    }
    -2.30
    ."
    -2.23
     будто
    -2.22
    瘩
    -2.22
    y
    -2.20
    POSITIVE LOGITS
     широкий
    2.55
    ?”
    2.45
     Чтобы
    2.30
     
    2.28
     кухо
    2.28
    依照
    2.25
    感じで
    2.23
     Для
    2.23
     Inspired
    2.19
     terminó
    2.19
    Activations Density 0.003%

    No Known Activations