© 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. 128245
    Prev
    Next
    INDEX
    Explanations

    statements of opinion

    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
    uaian
    -1.95
     Aucun
    -1.82
    %;
    -1.80
    asanjo
    -1.78
    LayoutConstraint
    -1.78
     они
    -1.77
    trecht
    -1.74
    URIDAD
    -1.73
    VIATIONS
    -1.73
     Alongside
    -1.73
    POSITIVE LOGITS
    入った
    2.00
    赑
    1.99
    en
    1.92
     OPINION
    1.92
    鹮
    1.86
     opinion
    1.80
    ea
    1.79
    </h3>
    1.78
    きちんと
    1.71
    菝
    1.70
    Activations Density 0.037%

    No Known Activations