© 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. 95397
    Prev
    Next
    INDEX
    Explanations

    list or tuple formatting

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

    The neuron activates on numeric tokens (sequences of digits) in the text.

    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
    final
    -0.80
     as
    -0.79
    berfläche
    -0.78
     of
    -0.78
    Other
    -0.75
    ادگی
    -0.75
    FetchType
    -0.74
    nelse
    -0.74
     only
    -0.73
     before
    -0.73
    POSITIVE LOGITS
    Belgique
    0.95
     많은
    0.91
     fabulous
    0.91
     immense
    0.90
     niekoľ
    0.88
    等は
    0.87
    fungsi
    0.87
    kenny
    0.86
     içeris
    0.85
    nze
    0.85
    Activations Density 0.036%

    No Known Activations