© 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. 45293
    Prev
    Next
    INDEX
    Explanations

    conditions for official bodies

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

    code, programming, and functions

    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
    Hints
    0.51
    ক্ষিতে
    0.51
     hints
    0.49
    Visible
    0.49
    ن
    0.49
    ন
    0.49
    Rendering
    0.48
    ج
    0.46
    Virtual
    0.46
    Renderer
    0.46
    POSITIVE LOGITS
     fizemos
    0.59
     equipos
    0.57
     bial
    0.57
     නිෂ්
    0.54
     supremely
    0.52
     echip
    0.52
     equipo
    0.52
     financieros
    0.51
     financière
    0.50
     respectfully
    0.49
    Activations Density 0.000%

    No Known Activations