© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40108
    Prev
    Next
    INDEX
    Explanations

    LaTeX and publication metadata

    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
    參考文獻
    -1.75
     on
    -1.70
    があり
    -1.58
    を
    -1.58
    <bos>
    -1.57
     where
    -1.55
    は
    -1.53
     from
    -1.52
     to
    -1.48
     with
    -1.48
    POSITIVE LOGITS
    様な
    2.14
    来週
    1.83
    為に
    1.78
    の方に
    1.75
    の方法
    1.71
     cómodo
    1.65
    おそ
    1.63
    つづく
    1.63
    を書く
    1.59
    ところに
    1.58
    Activations Density 0.001%

    No Known Activations