© 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. 22-GEMMASCOPE-RES-131K
    7. 26262
    Prev
    Next
    INDEX
    Explanations

    numbers and Love

    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
    どのような
    -1.71
    What
    -1.69
    From
    -1.62
    おわりに
    -1.56
    ܇
    -1.53
    When
    -1.48
    Where
    -1.44
    Everything
    -1.44
    部的
    -1.42
    淠
    -1.42
    POSITIVE LOGITS
    <bos>
    1.58
    もあります
    1.56
    などは
    1.39
    もありました
    1.38
    le
    1.35
    キス
    1.32
     svilupp
    1.28
    が
    1.27
    GRAFÍA
    1.23
    もある
    1.23
    Activations Density 0.000%

    No Known Activations