© 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. 85591
    Prev
    Next
    INDEX
    Explanations

    scarf or bandana

    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
     好看
    -2.58
     \
    -2.56
    臯
    -2.50
     unangemessene
    -2.45
    却又
    -2.39
    尛
    -2.36
     欣赏
    -2.34
    􀂃
    -2.33
     hijas
    -2.28
     Hinblick
    -2.25
    POSITIVE LOGITS
    e
    3.23
    on
    2.30
    to
    2.22
    t
    2.19
    I
    2.13
    ",
    2.11
    ’).
    2.09
    蟊
    2.08
     andra
    2.08
     herr
    2.03
    Activations Density 0.003%

    No Known Activations