© 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. 25967
    Prev
    Next
    INDEX
    Explanations

    addresses and zip codes

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

    powering or powered by

    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
    єдна
    0.57
     rougeâtres
    0.55
    гут
    0.54
    tiempo
    0.54
    ム
    0.52
    ည
    0.52
    今年も
    0.51
     vấn
    0.49
    глежда
    0.49
    ん
    0.49
    POSITIVE LOGITS
     of
    0.61
     from
    0.57
     Lif
    0.56
     Powered
    0.54
     Writing
    0.53
     White
    0.52
     on
    0.52
     GW
    0.52
     Ter
    0.51
     Landmark
    0.51
    Activations Density 0.037%

    No Known Activations