© 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. 10-GEMMASCOPE-RES-131K
    7. 90344
    Prev
    Next
    INDEX
    Explanations

    unspecified person

    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
    廡
    -1.52
     stück
    -1.51
     évidemment
    -1.50
     dám
    -1.48
     mío
    -1.47
    タグ
    -1.47
    有点
    -1.44
    πομπ
    -1.42
     commandé
    -1.40
    숱
    -1.40
    POSITIVE LOGITS
     to
    2.59
     with
    2.23
     from
    1.92
    </h1>
    1.88
     by
    1.82
    奋斗
    1.41
     and
    1.41
     案内
    1.34
     such
    1.31
     which
    1.30
    Activations Density 0.019%

    No Known Activations