© 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. 133644
    Prev
    Next
    INDEX
    Explanations

    medical issue or grievance

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

    law and order

    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
     मिलती
    0.47
    !</
    0.46
     scanners
    0.43
    ﹗
    0.43
    হ্যালো
    0.42
    alex
    0.42
    sensor
    0.42
    idone
    0.42
    Df
    0.41
    :${
    0.41
    POSITIVE LOGITS
     cinética
    0.48
    鰱
    0.48
    샛
    0.48
     Dá
    0.47
     Drž
    0.47
     Lest
    0.45
    후
    0.45
     Efter
    0.45
     Mout
    0.45
    cił
    0.45
    Activations Density 0.000%

    No Known Activations