© 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. 199610
    Prev
    Next
    INDEX
    Explanations

    Google Indeed Analytics branding

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

    document everything

    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
    υ
    0.44
    ח
    0.44
    olding
    0.43
     dewasa
    0.43
    🥡
    0.43
    ล็
    0.43
    ITION
    0.42
    ult
    0.42
    rito
    0.42
    כ
    0.42
    POSITIVE LOGITS
    تاجها
    0.47
    وني
    0.47
     meinem
    0.46
     اين
    0.45
     unten
    0.45
     praktisch
    0.45
     الشباب
    0.44
     الطالب
    0.43
     Trebuie
    0.43
     استعمال
    0.43
    Activations Density 0.000%

    No Known Activations