© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101998
    Prev
    Next
    INDEX
    Explanations

    nothing in

    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
     baumwolle
    -2.17
     estadounid
    -2.11
    鲧
    -1.93
     火鍋
    -1.89
    鲥
    -1.88
     vixion
    -1.82
    涐
    -1.82
     插图
    -1.82
    蔸
    -1.81
    澌
    -1.80
    POSITIVE LOGITS
    </strong>
    1.72
     de
    1.67
     *
    1.62
    場は
    1.56
    ).
    1.55
     (
    1.55
     ie
    1.53
     soothe
    1.52
     to
    1.51
     -
    1.48
    Activations Density 0.026%

    No Known Activations