© 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. 47786
    Prev
    Next
    INDEX
    Explanations

    contact locations and files

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

    resist adverse pressure, Libraries, Temp files

    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
     Americans
    0.47
     LOTRAchievement
    0.46
     Filipinos
    0.46
     सांस्कृतिक
    0.45
     synchronized
    0.44
     étrangers
    0.42
    <unused1080>
    0.42
    timer
    0.41
     folklor
    0.41
     Filipino
    0.41
    POSITIVE LOGITS
    에서
    0.51
    쯤
    0.47
     문의
    0.47
    기
    0.47
    면
    0.46
    인데
    0.46
    사
    0.46
    방
    0.45
    те
    0.44
    거
    0.44
    Activations Density 0.000%

    No Known Activations