© 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. 120617
    Prev
    Next
    INDEX
    Explanations

    possibility or suggestion

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

    toxic byproducts

    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
     róż
    0.50
     külön
    0.50
    ün
    0.50
     ແ
    0.50
     особы
    0.49
     мощности
    0.49
     پاب
    0.48
     либо
    0.48
     kiểu
    0.47
     वगैर
    0.47
    POSITIVE LOGITS
    t
    0.48
    ニット
    0.44
    en
    0.42
    eurs
    0.42
    vol
    0.41
    ))*
    0.40
    を受け
    0.40
     $*
    0.40
     braided
    0.39
    ルト
    0.39
    Activations Density 0.001%

    No Known Activations