© 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. 117071
    Prev
    Next
    INDEX
    Explanations

    medical clinic setting

    np_acts-logits-general · gemini-2.5-flash-lite

    places, entities, dates

    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
    ש
    0.52
    orate
    0.47
    嘭
    0.46
    Ever
    0.45
    Ian
    0.44
    Eu
    0.44
    Evan
    0.44
    ovirus
    0.44
    EVER
    0.44
    uero
    0.43
    POSITIVE LOGITS
     사례
    0.49
     Ā
    0.47
     mischievous
    0.45
     ကု
    0.45
    nim
    0.44
     Тро
    0.44
     disappears
    0.43
     adapts
    0.43
     lese
    0.43
     giz
    0.43
    Activations Density 0.000%

    No Known Activations