© 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. 129093
    Prev
    Next
    INDEX
    Explanations

    mobile app

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

    Butterfly clips, dots and dashes

    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
    ruction
    0.49
    倰
    0.48
    न्त्री
    0.48
     эффективности
    0.47
     fissures
    0.46
    кна
    0.46
     المصطلح
    0.46
    ม
    0.46
     چیز
    0.44
     сне
    0.44
    POSITIVE LOGITS
     Endpoint
    0.46
    TAP
    0.45
    port
    0.42
     tapa
    0.41
    مس
    0.41
    siz
    0.41
     piya
    0.41
     ===============
    0.41
    مت
    0.40
     média
    0.40
    Activations Density 0.001%

    No Known Activations