© 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. 48658
    Prev
    Next
    INDEX
    Explanations

    strict mode

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

    The neuron fires on numeral tokens—i.e. integer literals or numbers appearing in code or 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
     boxes
    -0.76
     household
    -0.75
    稿
    -0.70
     Boxes
    -0.70
    ະ
    -0.69
    household
    -0.68
    翦
    -0.67
    endios
    -0.66
    弟
    -0.66
    ケート
    -0.66
    POSITIVE LOGITS
    mode
    0.79
     mode
    0.79
    modes
    0.78
     widened
    0.76
    reading
    0.74
     modes
    0.73
     Mode
    0.73
     eradicated
    0.71
    ptr
    0.71
    Клуб
    0.71
    Activations Density 0.034%

    No Known Activations