© 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. 79616
    Prev
    Next
    INDEX
    Explanations

    youtube videos, factors, fail to, hazards, folder

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

    rescue, file, numbers, mort, generation

    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
     Jahrhund
    0.47
     たら
    0.46
     Фор
    0.46
    ereur
    0.46
    *.
    0.45
     связан
    0.45
    nal
    0.44
    sa
    0.44
    unsch
    0.44
     приви
    0.44
    POSITIVE LOGITS
     hydrolysis
    0.57
    ة
    0.57
    ing
    0.49
     sopr
    0.48
    ق
    0.46
     Synod
    0.46
    ស់
    0.45
    داد
    0.45
    чаем
    0.45
     fluctuation
    0.44
    Activations Density 0.000%

    No Known Activations