© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103556
    Prev
    Next
    INDEX
    Explanations

    strength and capability

    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
     through
    -2.27
     in
    -2.02
     for
    -2.02
     uses
    -1.91
     with
    -1.81
     intensely
    -1.78
     it
    -1.73
    után
    -1.72
     all
    -1.67
     unusually
    -1.67
    POSITIVE LOGITS
    ឵
    1.74
    ſu
    1.66
     breathtaking
    1.66
    有不少
    1.53
     dando
    1.51
     doo
    1.48
    焌
    1.48
     erheblich
    1.46
     correto
    1.45
    伥
    1.45
    Activations Density 0.002%

    No Known Activations