© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 24998
    Prev
    Next
    INDEX
    Explanations

    files and code snippets

    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
    Negative Logits
     their
    -1.07
     juillet
    -1.05
    álny
    -0.97
    Πηγές
    -0.95
     financière
    -0.95
     either
    -0.94
    或是
    -0.94
     materiais
    -0.94
     mixta
    -0.92
    힘
    -0.92
    POSITIVE LOGITS
    ⅝
    1.04
     personalità
    1.03
     vostre
    0.99
     profondità
    0.99
    אני
    0.99
     crescita
    0.99
    この記事
    0.98
     mangiare
    0.98
    ⅜
    0.98
     cammin
    0.97
    Activations Density 0.000%

    No Known Activations