© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14813
    Prev
    Next
    INDEX
    Explanations

    artist names

    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_22/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
     Other
    -2.92
    有一些
    -2.75
    ".
    -2.73
     Our
    -2.67
    2
    -2.45
    ra
    -2.44
    」
    -2.39
    Y
    -2.38
     '
    -2.34
    u
    -2.31
    POSITIVE LOGITS
    渽
    2.53
    ꦠ
    2.38
    Lack
    2.36
    啭
    2.30
    ᥫ
    2.30
    apatalk
    2.27
     矢量
    2.22
    ଂ
    2.19
    بيس
    2.17
    苁
    2.17
    Activations Density 0.010%

    No Known Activations