© 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. 21321
    Prev
    Next
    INDEX
    Explanations

    JSF

    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
    酲
    -1.48
    Více
    -1.38
    What
    -1.32
    是什么意思
    -1.32
    There
    -1.30
    Dicas
    -1.30
     Having
    -1.28
    Tipps
    -1.25
    Temporada
    -1.24
    Děkuji
    -1.23
    POSITIVE LOGITS
     preparados
    1.64
     sprawy
    1.63
     preparado
    1.41
    らかに
    1.39
     EVEN
    1.38
    棡
    1.38
     zach
    1.35
     twarzy
    1.34
    ޏ
    1.34
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.33
    Activations Density 0.020%

    No Known Activations