© 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. 79835
    Prev
    Next
    INDEX
    Explanations

    Q:, To, Oreo

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

    The neuron activates on numeric tokens (digits and 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
     at
    -1.99
     as
    -1.86
     after
    -1.84
     with
    -1.81
     from
    -1.79
     for
    -1.77
     if
    -1.73
     since
    -1.72
     even
    -1.67
     before
    -1.66
    POSITIVE LOGITS
     extré
    1.69
    ཥ
    1.50
     ouvrir
    1.45
     pattes
    1.41
     splendid
    1.40
     ſtre
    1.38
     côtes
    1.38
    翃
    1.34
     goofy
    1.34
    exemple
    1.34
    Activations Density 0.001%

    No Known Activations