© 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. 22-GEMMASCOPE-RES-131K
    7. 14022
    Prev
    Next
    INDEX
    Explanations

    new list append data JSON Optional pd helper

    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
     can
    -1.40
     違い
    -1.17
     even
    -1.11
    課題
    -1.02
     since
    -0.95
     deaktivi
    -0.95
     majorité
    -0.90
    왕
    -0.89
    特的
    -0.88
     later
    -0.88
    POSITIVE LOGITS
     sœurs
    1.21
     vendedores
    1.14
    celotti
    1.13
    outa
    1.13
    thee
    1.12
     billeder
    1.12
    ⚙
    1.11
    ibold
    1.08
     nossos
    1.05
    あぁ
    1.04
    Activations Density 0.013%

    No Known Activations