© 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. 124600
    Prev
    Next
    INDEX
    Explanations

    citations or figures

    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
    錨
    -2.81
     это
    -2.70
    }
    -2.66
    );
    -2.44
    すぎる
    -2.38
    いえば
    -2.17
    釦
    -2.17
     dieser
    -2.17
     '
    -2.16
     attentive
    -2.14
    POSITIVE LOGITS
    y
    3.02
    筇
    2.52
    糨
    2.50
    镦
    2.45
     aveva
    2.39
     \[
    2.31
     вижу
    2.30
     dirigente
    2.27
     Logement
    2.27
    arão
    2.20
    Activations Density 0.023%

    No Known Activations