© 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. 53580
    Prev
    Next
    INDEX
    Explanations

    transmit large amounts

    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
    [
    0.49
    •
    0.46
    .
    0.45
    these
    0.44
    First
    0.43
     I
    0.43
    *
    0.43
     Ху
    0.43
    neo
    0.43
    lab
    0.41
    POSITIVE LOGITS
     wład
    0.53
     druż
    0.52
     способом
    0.50
    㗎
    0.50
     liht
    0.50
     destra
    0.50
    ເລັກ
    0.49
     lender
    0.49
    صبح
    0.49
     stadion
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.