© 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. 84308
    Prev
    Next
    INDEX
    Explanations

    dear man

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

    anatomy, options, other languages

    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
     Snakes
    0.42
     са
    0.42
    riving
    0.42
    yards
    0.42
    College
    0.42
     جواز
    0.42
     Х
    0.41
     specifies
    0.41
    lifetime
    0.41
    living
    0.41
    POSITIVE LOGITS
    鬼
    0.49
    harusnya
    0.48
    δη
    0.46
    šu
    0.45
    没人
    0.44
    操作系统
    0.43
     området
    0.43
    ipkan
    0.43
     відбу
    0.43
     były
    0.43
    Activations Density 0.001%

    No Known Activations