© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67870
    Prev
    Next
    INDEX
    Explanations

    code identifiers followed by punctuation

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

    This neuron activates on sub-tokens of camelCase or PascalCase identifiers in code (i.e., the individual capitalized words or suffixes inside multiword function, class, or variable names).

    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
     pozosta
    -1.41
     soste
    -1.33
     maxx
    -1.32
     Ure
    -1.30
     uomini
    -1.29
     minori
    -1.29
     animali
    -1.27
    ètement
    -1.27
     『
    -1.27
     ultimi
    -1.26
    POSITIVE LOGITS
     in
    1.60
     about
    1.56
     on
    1.56
     like
    1.51
     the
    1.51
    archical
    1.48
     of
    1.45
    ()]);
    1.28
     AQUÍ
    1.26
     apasion
    1.25
    Activations Density 0.056%

    No Known Activations