© 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. 10-GEMMASCOPE-RES-131K
    7. 70983
    Prev
    Next
    INDEX
    Explanations

    great + descriptive noun

    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
    ൎ
    -1.88
    ⁛
    -1.83
     sinnvoll
    -1.83
     vielfach
    -1.81
     景点
    -1.80
     füh
    -1.78
    𖤣
    -1.78
    盦
    -1.77
     verschieden
    -1.76
    驺
    -1.73
    POSITIVE LOGITS
     strides
    1.58
    >
    1.53
    {\$
    1.52
    Not
    1.51
    </h5>
    1.50
    良好的
    1.48
    );
    1.48
    Just
    1.47
    のは
    1.47
     .
    1.46
    Activations Density 0.089%

    No Known Activations