© 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. 128844
    Prev
    Next
    INDEX
    Explanations

    as a sequel

    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
    有两
    -2.56
    最后由
    -2.48
    ープン
    -2.44
    というわけで
    -2.44
    葑
    -2.38
    ֢
    -2.36
    不明白
    -2.31
     agile
    -2.27
    珰
    -2.25
     tries
    -2.23
    POSITIVE LOGITS
     —
    2.86
     Gefühle
    2.55
     就
    2.44
     Empfindung
    2.41
     imbued
    2.30
     Konsequ
    2.28
     jahre
    2.28
     принять
    2.27
     Erlebn
    2.25
    </h4>
    2.20
    Activations Density 0.000%

    No Known Activations