© 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. 201186
    Prev
    Next
    INDEX
    Explanations

    words following specific tokens

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

    history, rates, time, factor

    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
     مللي
    0.44
     endothelial
    0.43
    categorias
    0.43
     crumbled
    0.43
     soluciones
    0.42
     ves
    0.41
    ↵↵↵↵↵↵
    0.41
     uncomplicated
    0.41
    ě
    0.41
     shredded
    0.40
    POSITIVE LOGITS
    익
    0.54
    라
    0.54
    奖
    0.52
    竣工
    0.51
    자의
    0.51
    питан
    0.50
    탑
    0.50
    에
    0.50
    冂
    0.50
    자가
    0.49
    Activations Density 0.000%

    No Known Activations