© 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. 34-GEMMASCOPE-RES-131K
    7. 92862
    Prev
    Next
    INDEX
    Explanations

    licenses and code

    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_34/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
    為に
    -1.73
    すっ
    -1.39
    ところに
    -1.35
    際は
    -1.32
    ほら
    -1.28
    際には
    -1.28
    あー
    -1.28
    喏
    -1.25
    の方に
    -1.25
    様な
    -1.24
    POSITIVE LOGITS
    そして
    1.39
    が
    1.25
    方針
    1.22
    <bos>
    1.20
    を
    1.20
     mainly
    1.16
    結局
    1.13
    かで
    1.11
    動物園
    1.10
     for
    1.09
    Activations Density 0.155%

    No Known Activations