© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 44190
    Prev
    Next
    INDEX
    Explanations

    years, UK, 0, collecting, our, contemporary, pulse, Corporation, they, holidays, immediately, handbook

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

    modern language, website, fits best

    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
     тренер
    0.44
    簍
    0.43
    폈
    0.43
    和大
    0.42
    ットフォーム
    0.42
     reaper
    0.41
     গার্ডিয়ান
    0.41
     геро
    0.41
    bgColor
    0.41
     domestically
    0.41
    POSITIVE LOGITS
    อะไร
    0.55
    ม
    0.52
    的点
    0.49
    }}}
    0.46
     colours
    0.46
    ‘’
    0.45
    ब्द
    0.44
    喏
    0.44
    resolve
    0.44
    im
    0.43
    Activations Density 0.000%

    No Known Activations