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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76242
    Prev
    Next
    INDEX
    Explanations

    apoptosis or router configuration

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

    The neuron tends to fire most strongly on longer, content‐bearing tokens (e.g. technical terms, multisyllabic words, proper names, and other substantial vocabulary) rather than short function words.

    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
    烈的
    -0.71
     luces
    -0.70
    maro
    -0.69
    inales
    -0.67
     egész
    -0.66
    waan
    -0.66
    网站
    -0.65
     Untold
    -0.65
    rero
    -0.63
     prefier
    -0.63
    POSITIVE LOGITS
    údo
    0.80
    轆
    0.69
     CURIAM
    0.66
     procur
    0.65
    udu
    0.64
    輓
    0.64
    APIView
    0.63
     Juden
    0.63
    ؤول
    0.63
    Ответить
    0.63
    Activations Density 0.044%

    No Known Activations