© 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. 39843
    Prev
    Next
    INDEX
    Explanations

    Microsoft Microsoft

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

    tokens, context, limits

    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
     are
    0.53
     வில்
    0.52
     och
    0.52
     is
    0.50
    weather
    0.50
     wd
    0.48
    hl
    0.48
     V
    0.47
    wd
    0.47
     እንደ
    0.47
    POSITIVE LOGITS
    定義
    0.59
    функ
    0.59
    に至
    0.54
    ⃙
    0.54
    伝統
    0.52
    一時
    0.52
    ῇ
    0.51
    生徒
    0.50
    苙
    0.50
    情形
    0.50
    Activations Density 0.000%

    No Known Activations