© 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. 38724
    Prev
    Next
    INDEX
    Explanations

    URLs and non-Latin characters

    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
     When
    -3.16
     There
    -2.94
     Furthermore
    -2.83
     Apparently
    -2.73
     It
    -2.70
    There
    -2.69
     Finally
    -2.66
     Obviously
    -2.66
     Evidently
    -2.64
     However
    -2.63
    POSITIVE LOGITS
    茕
    2.80
     nimmer
    2.64
    蹀
    2.58
    c
    2.52
     bluz
    2.47
    ین
    2.45
     vectorstock
    2.42
     projek
    2.42
    ágenes
    2.34
    퐼
    2.34
    Activations Density 0.016%

    No Known Activations