© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25408
    Prev
    Next
    INDEX
    Explanations

    code endings

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

    The neuron fires on ordinary variable or parameter identifiers in code.

    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
     to
    -2.27
     for
    -2.13
     from
    -2.05
     with
    -1.92
     of
    -1.88
     in
    -1.77
     by
    -1.73
     S
    -1.60
     A
    -1.58
     The
    -1.56
    POSITIVE LOGITS
     NEGRO
    1.90
     ESTR
    1.83
     DOMINGO
    1.82
     kulak
    1.79
     monstru
    1.77
     masaj
    1.74
     広場
    1.67
     JULIO
    1.67
    Кан
    1.66
    焢
    1.66
    Activations Density 0.106%

    No Known Activations