© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 233823
    Prev
    Next
    INDEX
    Explanations

    names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     給
    0.48
     ਸਮ
    0.47
     なかっ
    0.46
     ਕਿ
    0.46
    <unused25>
    0.45
     capacidades
    0.44
     過
    0.43
    葦
    0.43
     紹介
    0.43
    EndInit
    0.43
    POSITIVE LOGITS
    Traffic
    0.45
     Timothy
    0.43
     Trump
    0.43
     Stephen
    0.43
     John
    0.42
     Town
    0.41
    就这样
    0.41
     James
    0.41
     khắp
    0.41
     will
    0.40
    Activations Density 0.001%

    No Known Activations