© 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. 117563
    Prev
    Next
    INDEX
    Explanations

    abstract documentation

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

    The neuron specializes in spotting numeric tokens (e.g. numbers, parameter values, units) and related metadata in technical or markup 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
     Zeits
    -0.72
    zamos
    -0.69
     動画
    -0.66
    Balance
    -0.65
    Norge
    -0.65
     Teraz
    -0.65
    ressum
    -0.65
    自动
    -0.63
    reya
    -0.63
    激烈
    -0.63
    POSITIVE LOGITS
    ondon
    0.73
    COLLECT
    0.72
     Baron
    0.72
    RectangleBorder
    0.68
    IONI
    0.68
    binder
    0.67
     Sl
    0.65
     congregation
    0.65
    已被
    0.65
     Serge
    0.65
    Activations Density 0.063%

    No Known Activations