© 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. 161517
    Prev
    Next
    INDEX
    Explanations

    lens, high quality, chance, from

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

    app documentation, targeting, building, tracking

    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
     музи
    0.53
    BURTS
    0.52
     букмекеры
    0.52
     ಬಂದ
    0.51
    simplex
    0.48
    暁
    0.48
     माध्यमा
    0.47
    $};
    0.47
    Midnight
    0.47
    গ্রহায়ণ
    0.46
    POSITIVE LOGITS
    نه
    0.62
    وم
    0.60
     Succ
    0.54
    用
    0.52
    是用
    0.52
     Provincia
    0.51
    ن
    0.50
     Config
    0.50
     schrift
    0.49
     fron
    0.49
    Activations Density 0.001%

    No Known Activations