© 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. 9473
    Prev
    Next
    INDEX
    Explanations

    kitchen cabinet hardware

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

    statement termination

    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
    Kya
    0.43
     annih
    0.43
    出来ない
    0.39
     いき
    0.38
    蹉
    0.38
     Choibalsan
    0.38
    嬋
    0.38
     نہ
    0.37
    🏥
    0.37
    鵡
    0.37
    POSITIVE LOGITS
    льные
    0.44
     ley
    0.44
     ኢን
    0.40
    x
    0.40
    лежа
    0.39
     Springfield
    0.38
    тные
    0.37
     Midland
    0.37
     concentrated
    0.36
     Ley
    0.36
    Activations Density 0.011%

    No Known Activations