© 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. 27429
    Prev
    Next
    INDEX
    Explanations

    specific follow-ups

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

    jab

    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
    .
    0.57
     despite
    0.50
     north
    0.49
     those
    0.45
     although
    0.45
     that
    0.45
    despite
    0.45
     which
    0.44
    is
    0.44
    st
    0.42
    POSITIVE LOGITS
    ेंटीना
    0.57
    ScriptBuf
    0.53
    部分は
    0.51
    衤
    0.50
    ecimiento
    0.49
     обору
    0.49
    はじ
    0.49
     додат
    0.48
    部分
    0.47
    还会
    0.47
    Activations Density 0.000%

    No Known Activations