© 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. 242424
    Prev
    Next
    INDEX
    Explanations

    the seat is still unoccupied

    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
    த்தினை
    0.48
     Omni
    0.45
    hoes
    0.44
     Clancy
    0.44
    сии
    0.43
    也就是
    0.42
    主義
    0.42
    勇
    0.42
    ভাবে
    0.41
     япон
    0.41
    POSITIVE LOGITS
     そこ
    0.49
     disparition
    0.47
     blanchâtre
    0.47
     提供
    0.46
     ಏಕೆಂದರೆ
    0.46
     కమి
    0.46
     pentes
    0.44
    arında
    0.44
     ແລະ
    0.43
     parametri
    0.43
    Activations Density 0.000%

    No Known Activations