© 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. 66468
    Prev
    Next
    INDEX
    Explanations

    keyword followed by descriptor

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

    This neuron identifies occurrences of the exact token “string” in code (e.g. as in frozen_string_literal).

    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
     on
    -1.78
     of
    -1.69
     their
    -1.68
     you
    -1.63
     what
    -1.61
     all
    -1.53
     in
    -1.45
     or
    -1.45
     more
    -1.45
     and
    -1.44
    POSITIVE LOGITS
     Sortiment
    1.66
    ܆
    1.57
    Hilsen
    1.56
    Nieuwe
    1.48
    chtenstein
    1.45
    ㈬
    1.45
    بسم
    1.42
     COULD
    1.42
    Aantal
    1.41
     カットソー
    1.41
    Activations Density 0.000%

    No Known Activations