© 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. 64128
    Prev
    Next
    INDEX
    Explanations

    series of academic conferences

    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
     Yue
    -0.76
    RAN
    -0.76
    KEYS
    -0.75
    igl
    -0.75
    koord
    -0.73
    لان
    -0.72
    wę
    -0.72
     zá
    -0.72
    ТИ
    -0.71
     moletom
    -0.71
    POSITIVE LOGITS
     власть
    0.77
     believe
    0.73
     Toxicology
    0.73
     udě
    0.73
     Aufnahme
    0.71
     "",
    0.70
     declare
    0.69
     höch
    0.69
     Emphasis
    0.68
    たとえば
    0.68
    Activations Density 0.088%

    No Known Activations