© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128448
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens or values (digits or numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    lists of variables or items

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     bê
    -1.69
    殽
    -1.66
     quí
    -1.65
     mélanger
    -1.64
     soms
    -1.63
    ̴
    -1.63
     verbe
    -1.62
    ≅
    -1.60
    ∅
    -1.60
     TÉ
    -1.60
    POSITIVE LOGITS
     and
    3.11
     or
    1.92
     until
    1.61
     for
    1.49
     but
    1.43
     During
    1.41
     while
    1.41
     has
    1.36
     Since
    1.34
     if
    1.34
    Activations Density 0.043%

    No Known Activations