© 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. 10-GEMMASCOPE-RES-131K
    7. 128217
    Prev
    Next
    INDEX
    Explanations

    a variety of

    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
     Öffnen
    -2.25
    8
    -2.17
    
    -2.13
     hầu
    -2.11
     einzigen
    -2.05
     faisant
    -1.99
     deta
    -1.98
     vorigen
    -1.97
    
    -1.92
     teniendo
    -1.91
    POSITIVE LOGITS
     sés
    2.47
    瑧
    2.33
    見て
    2.02
     espé
    2.02
     förstå
    2.00
    られて
    1.95
     snabbt
    1.95
     riche
    1.91
    ánicas
    1.91
     peines
    1.91
    Activations Density 0.034%

    No Known Activations