© 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. 157247
    Prev
    Next
    INDEX
    Explanations

    officer information summary

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

    materials, frequency, updates, shade, screws

    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
     odio
    0.55
    λώ
    0.47
     โจทย์
    0.47
    Исход
    0.47
    влено
    0.46
     nuestra
    0.46
    Historia
    0.45
    谶
    0.45
    反对
    0.45
    Pand
    0.45
    POSITIVE LOGITS
     führ
    0.44
     هایی
    0.42
     ট
    0.42
     ক্র
    0.41
    馬上
    0.41
     oversees
    0.40
     विद्यु
    0.39
     giám
    0.39
    穩定
    0.38
    هاي
    0.38
    Activations Density 0.001%

    No Known Activations