© 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. 70471
    Prev
    Next
    INDEX
    Explanations

    tickets and use

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

    companies and global reach

    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
     pronotum
    0.54
     holotype
    0.47
     wildflower
    0.46
     rambling
    0.45
     catchy
    0.45
     wildflowers
    0.45
     vecchio
    0.43
    裄
    0.43
     regarder
    0.43
     ponytail
    0.43
    POSITIVE LOGITS
    🚀
    0.50
    模块
    0.48
     डेवल
    0.48
    编写
    0.48
     Middleware
    0.48
    最优
    0.48
     выборах
    0.48
    u
    0.48
    考试
    0.47
    团队
    0.46
    Activations Density 0.003%

    No Known Activations