© 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. 10-GEMMASCOPE-RES-131K
    7. 128418
    Prev
    Next
    INDEX
    Explanations

    utopian and dystopian concepts

    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_10/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
    哢
    -2.61
     inta
    -2.33
    涠
    -2.25
    豨
    -2.25
    ㊤
    -2.23
     praktische
    -2.22
    ть
    -2.22
     gustaMe
    -2.20
    蜮
    -2.20
    !"
    -2.19
    POSITIVE LOGITS
    {
    2.92
    [
    2.64
    *
    2.56
    ↵
    2.33
    Other
    2.25
    e
    2.25
    (
    2.17
     parlak
    2.09
    .
    2.08
     Other
    2.06
    Activations Density 0.011%

    No Known Activations