© 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. 195645
    Prev
    Next
    INDEX
    Explanations

    changes and politics

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

    feature detection

    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
    lás
    0.54
    portál
    0.54
    PhCH
    0.49
     pérd
    0.49
    %",
    0.48
     तूती
    0.48
    bestroute
    0.47
     ऑक्सी
    0.47
    +{\
    0.47
     QuantityOnHand
    0.46
    POSITIVE LOGITS
     Co
    0.47
     Eul
    0.46
     THEORY
    0.46
    и
    0.46
     H
    0.45
    на
    0.45
    지
    0.45
     F
    0.45
    ges
    0.45
     Ex
    0.44
    Activations Density 0.000%

    No Known Activations