© 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. 65233
    Prev
    Next
    INDEX
    Explanations

    classes after "fu"

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

    searches, divisibility, bridge

    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
    ʕ
    0.53
     ઉત્
    0.50
    uatan
    0.48
    hooter
    0.48
    gunta
    0.47
    ᱷ
    0.47
     soglas
    0.46
     پہا
    0.46
     આજે
    0.46
     ಮಾ
    0.46
    POSITIVE LOGITS
    데
    0.47
    та
    0.46
    Мен
    0.44
     тра
    0.42
    Авто
    0.42
     faz
    0.41
    .${
    0.41
    粒
    0.41
     Move
    0.41
     DAVIS
    0.41
    Activations Density 0.000%

    No Known Activations