© 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. 228144
    Prev
    Next
    INDEX
    Explanations

    medical, procedural, or fan-related contexts

    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
    紂
    0.46
     soak
    0.45
    所に
    0.45
    ধ্য
    0.45
    CCCCCC
    0.45
    身長
    0.45
     কেবলমাত্র
    0.44
     moan
    0.43
     下さい
    0.43
    leep
    0.43
    POSITIVE LOGITS
     и
    0.48
     és
    0.46
     Orthodox
    0.46
     unorthodox
    0.45
    ([^
    0.44
    ،
    0.43
     گا
    0.43
    *_
    0.43
     Hashimoto
    0.42
     Hud
    0.41
    Activations Density 0.000%

    No Known Activations