© 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. 78736
    Prev
    Next
    INDEX
    Explanations

    code definition and classes

    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
     SYS
    -0.72
     Permanent
    -0.71
     Ano
    -0.68
     Kon
    -0.68
     shoreline
    -0.68
     phải
    -0.67
    gien
    -0.66
     permanent
    -0.65
     Quantity
    -0.64
    cfa
    -0.64
    POSITIVE LOGITS
    点此举报
    0.71
    Podob
    0.68
    Zdroj
    0.68
    êtements
    0.66
    nofollow
    0.66
     飛
    0.65
    tım
    0.65
    يتر
    0.65
    getProject
    0.65
    olstein
    0.65
    Activations Density 0.074%

    No Known Activations