© 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. 72899
    Prev
    Next
    INDEX
    Explanations

    $$ mathematical equations

    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
     والأ
    -1.27
    おわりに
    -1.25
    明日は
    -1.13
    既に
    -1.13
    <<<<<<<
    -1.12
     والق
    -1.12
     européenne
    -1.11
    ән
    -1.08
    来到了
    -1.08
    さぁ
    -1.05
    POSITIVE LOGITS
    荩
    1.48
    看一下
    1.23
     Produkten
    1.20
    你喜欢
    1.18
     która
    1.17
     in
    1.16
     AUTHORITIES
    1.14
    ngày
    1.13
    注意事项
    1.13
     Mitgliedern
    1.13
    Activations Density 0.002%

    No Known Activations