© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71932
    Prev
    Next
    INDEX
    Explanations

    #define constants

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

    The neuron activates on numeric tokens (including integers, decimals, and measurement values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Interes
    -1.98
     チラ
    -1.95
     стоковые
    -1.87
    reasons
    -1.85
     花纹
    -1.82
    tych
    -1.79
    montage
    -1.79
    aning
    -1.77
     tafel
    -1.77
     alcune
    -1.73
    POSITIVE LOGITS
     to
    2.33
     if
    2.11
     from
    2.09
     that
    1.97
     If
    1.94
     has
    1.84
     +
    1.80
     provide
    1.78
     your
    1.77
     which
    1.76
    Activations Density 0.004%

    No Known Activations