© 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. 76647
    Prev
    Next
    INDEX
    Explanations

    Economics and academic institutions

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

    divergence, Rippling, string, automatically

    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
    㧿
    0.53
     किमान
    0.52
    <unused998>
    0.52
     因為
    0.52
    though
    0.52
     फ्रेंड्स
    0.50
    ودي
    0.50
    之後
    0.48
     ওভার
    0.48
     следу
    0.48
    POSITIVE LOGITS
     (
    0.57
    /
    0.52
     Melt
    0.47
     dramat
    0.46
     its
    0.46
     broker
    0.45
     mund
    0.45
     brok
    0.45
     glas
    0.45
     sensit
    0.44
    Activations Density 0.000%

    No Known Activations