© 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. 33651
    Prev
    Next
    INDEX
    Explanations

    Broadcast Receiver, Adventure Lover, Criminal Charges, Produce Section

    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
     judgmental
    0.49
    0.49
    聡
    0.47
    -
    0.46
    ate
    0.44
    boards
    0.42
     Slovakia
    0.41
     DOES
    0.41
     COVID
    0.41
     Mongolia
    0.41
    POSITIVE LOGITS
    ل
    0.56
    د
    0.55
    觫
    0.53
     тер
    0.51
     рее
    0.49
    rebbero
    0.48
    т
    0.48
    癹
    0.47
     پیدا
    0.47
     لف
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.