© 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. 22-GEMMASCOPE-RES-131K
    7. 128244
    Prev
    Next
    INDEX
    Explanations

    // SPDX, Effect of, namespace, The present

    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_22/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
     cará
    -1.07
    而非
    -0.97
    //[
    -0.97
    НС
    -0.95
    pulumi
    -0.94
     พ
    -0.94
    𝚃
    -0.93
     Introducción
    -0.92
     puertos
    -0.91
    ראלי
    -0.91
    POSITIVE LOGITS
     elig
    0.97
     Darin
    0.97
     with
    0.94
     rapporte
    0.93
     and
    0.91
    УДК
    0.91
    ki
    0.90
     یا
    0.90
     roberto
    0.88
     Organiser
    0.88
    Activations Density 0.000%

    No Known Activations