© 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. 83314
    Prev
    Next
    INDEX
    Explanations

    years old and status

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

    arrays equal

    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
    τρέ
    0.39
    тию
    0.39
    ଥି
    0.38
    エントリー
    0.37
    顯示
    0.36
    ኮ
    0.36
    申請
    0.35
    強調
    0.35
     assunto
    0.35
    まずは
    0.35
    POSITIVE LOGITS
     mêmes
    0.36
    គ្ន
    0.36
     Beet
    0.35
     Bridgewater
    0.35
     കി
    0.34
    लोर
    0.33
     Beur
    0.33
     బీ
    0.33
     منا
    0.32
    бна
    0.32
    Activations Density 0.623%

    No Known Activations