© 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. 31532
    Prev
    Next
    INDEX
    Explanations

    English language markers

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

    utf-8 character encoding and 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
     slender
    0.46
    xmin
    0.45
     Mat
    0.45
     tokamak
    0.45
     unim
    0.44
    婼
    0.44
     ट्रैक्टर
    0.44
    runk
    0.43
     thụ
    0.43
     Fowler
    0.42
    POSITIVE LOGITS
     содержимое
    0.47
     cinese
    0.44
     sadrž
    0.44
    汉语
    0.42
    સ
    0.42
     idioma
    0.41
    CHINA
    0.41
     जातीय
    0.41
     mês
    0.39
    لمانيا
    0.39
    Activations Density 0.000%

    No Known Activations