© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86609
    Prev
    Next
    INDEX
    Explanations

    helping others

    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
     têtes
    -1.30
     lanzó
    -1.30
     perles
    -1.29
    窰
    -1.26
     comprando
    -1.23
     leeftijd
    -1.22
    ﻦ
    -1.20
    谂
    -1.20
     ними
    -1.19
     rapides
    -1.18
    POSITIVE LOGITS
     and
    1.43
    </b>
    1.30
     not
    1.28
     there
    1.20
     no
    1.19
     so
    1.19
    <bos>
    1.16
     モン
    1.14
     public
    1.14
     sufferers
    1.12
    Activations Density 0.050%

    No Known Activations