© 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. 67998
    Prev
    Next
    INDEX
    Explanations

    numbers counting instances

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

    The neuron chiefly activates on numeric tokens (digits or number words).

    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
    fällt
    -1.45
     farby
    -1.38
     konfigura
    -1.34
    鳚
    -1.33
    ᐳ
    -1.30
     レスト
    -1.29
     éta
    -1.27
     multicolore
    -1.27
    蚰
    -1.27
     bandes
    -1.24
    POSITIVE LOGITS
     also
    2.70
     for
    1.69
    Also
    1.63
     in
    1.60
     Also
    1.59
     different
    1.54
     "
    1.52
     of
    1.45
    also
    1.41
    I
    1.36
    Activations Density 0.033%

    No Known Activations