© 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. 232980
    Prev
    Next
    INDEX
    Explanations

    of

    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
    的基本
    0.59
    基础
    0.47
    誼
    0.47
    綁
    0.46
    樣本
    0.46
     револю
    0.46
    dictionary
    0.45
    相對
    0.45
    ሕ
    0.45
    ايات
    0.44
    POSITIVE LOGITS
     hasil
    0.52
     elektrom
    0.50
     akt
    0.49
     garner
    0.48
     incandescent
    0.48
     miesią
    0.47
    श्त
    0.46
     อัน
    0.45
     ornamentation
    0.45
    ania
    0.44
    Activations Density 0.000%

    No Known Activations