© 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. 90940
    Prev
    Next
    INDEX
    Explanations

    php orm annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     italic
    -0.77
     Helmet
    -0.72
    信任
    -0.71
     Zé
    -0.71
    |[
    -0.71
    achievement
    -0.70
    LoS
    -0.69
    帕
    -0.68
     Entrada
    -0.67
    tät
    -0.67
    POSITIVE LOGITS
    Sabah
    0.79
     起
    0.78
    zyk
    0.78
    guard
    0.77
     legitimate
    0.76
    ଭ
    0.76
    起到
    0.75
    blumen
    0.75
     also
    0.75
    imes
    0.74
    Activations Density 0.005%

    No Known Activations