© 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. 34-GEMMASCOPE-RES-131K
    7. 31481
    Prev
    Next
    INDEX
    Explanations

    growing or increasing

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

    The neuron selectively activates on numeric tokens, i.e. it detects numbers and numerical values 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_34/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
     ща
    -0.77
     Teixeira
    -0.77
     libre
    -0.76
     indu
    -0.75
     teatro
    -0.72
     tử
    -0.71
     AUDIO
    -0.71
    ksa
    -0.70
     externa
    -0.70
     Famille
    -0.69
    POSITIVE LOGITS
    rachel
    0.75
    dieux
    0.73
     huidige
    0.73
    idr
    0.73
    춥
    0.72
    ervor
    0.71
     ولو
    0.71
     financière
    0.71
    ))^{
    0.70
    cuentes
    0.70
    Activations Density 0.013%

    No Known Activations