© 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. 22-GEMMASCOPE-RES-131K
    7. 35838
    Prev
    Next
    INDEX
    Explanations

    Localization of

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

    The neuron fires on code identifiers—user-defined names such as variable, function, class, or module names (including snake_case, camelCase, hyphenated, or PascalCase 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_22/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
     conifers
    -0.91
    chauff
    -0.91
     adequada
    -0.87
     Gehir
    -0.86
    zają
    -0.85
    ilibre
    -0.85
     rapidamente
    -0.85
    reveal
    -0.84
     duidelijk
    -0.84
    ığımız
    -0.84
    POSITIVE LOGITS
    They
    0.94
     naudoti
    0.92
     dabar
    0.88
    ::*;
    0.86
     보기
    0.84
     دیده
    0.84
     juos
    0.83
    Being
    0.83
     alpina
    0.83
    '))
    0.82
    Activations Density 0.003%

    No Known Activations