© 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. 71632
    Prev
    Next
    INDEX
    Explanations

    door and its context

    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
    他的
    -1.71
    迢
    -1.61
    Decide
    -1.55
    s
    -1.52
    0
    -1.52
    друг
    -1.45
    3
    -1.44
    WRENCE
    -1.43
     хотел
    -1.39
    aller
    -1.38
    POSITIVE LOGITS
    辚
    1.95
    翆
    1.87
     è
    1.79
     เปิด
    1.73
     You
    1.72
    致力于
    1.67
     The
    1.66
     Why
    1.64
    羮
    1.63
     dopo
    1.60
    Activations Density 0.027%

    No Known Activations