© 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. 155540
    Prev
    Next
    INDEX
    Explanations

    location or when

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

    no discernible

    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
    eve
    0.54
    eal
    0.52
    on
    0.49
    一个
    0.48
    지만
    0.46
    以前
    0.46
    is
    0.45
    끔
    0.45
    ال
    0.44
    hut
    0.44
    POSITIVE LOGITS
    踮
    0.53
     ಡಿ
    0.51
     interesse
    0.50
     intérêt
    0.50
    版的
    0.48
    larına
    0.48
     Ladakh
    0.48
     می‌باشد
    0.47
    <unused755>
    0.47
    raž
    0.47
    Activations Density 0.000%

    No Known Activations