© 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. 40082
    Prev
    Next
    INDEX
    Explanations

    redirects and URLs

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

    This neuron detects tokens containing numerals (e.g. version numbers, IDs, line numbers).

    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
     lieben
    -0.89
    ссер
    -0.89
    насе
    -0.88
     hadir
    -0.88
     város
    -0.84
     harten
    -0.84
    AddColumn
    -0.82
    However
    -0.81
    Materiał
    -0.80
    vento
    -0.80
    POSITIVE LOGITS
    <%=
    1.10
    觐
    1.02
    Gir
    0.95
     Trunks
    0.93
     again
    0.92
     then
    0.92
    初め
    0.92
    ///<
    0.92
    unnitel
    0.90
    次は
    0.89
    Activations Density 0.004%

    No Known Activations