© 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. 58198
    Prev
    Next
    INDEX
    Explanations

    Previous OCD

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

    law enforcement and locations

    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
     forecasts
    0.54
    .<
    0.49
    自从
    0.48
    .*/
    0.47
    .\\
    0.47
    **.
    0.46
    earch
    0.46
     requires
    0.46
    😋
    0.45
    ım
    0.45
    POSITIVE LOGITS
     officers
    0.46
     NYPD
    0.46
     civilian
    0.45
     chiefs
    0.45
     homicide
    0.45
    ্কার
    0.43
     FBI
    0.43
     Clinton
    0.42
     Latina
    0.42
    殺人
    0.42
    Activations Density 0.000%

    No Known Activations