© 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. 25876
    Prev
    Next
    INDEX
    Explanations

    numbers and forty

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

    numbers and dates

    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
     دى
    0.42
    داشت
    0.39
    های
    0.39
    こういう
    0.38
    дол
    0.38
    خواست
    0.38
    삼
    0.38
    alaikumsalam
    0.38
    avasena
    0.37
    สาม
    0.37
    POSITIVE LOGITS
    4
    0.46
     Fourth
    0.45
     ४
    0.40
     fourth
    0.39
     sua
    0.39
     Work
    0.38
     चौथा
    0.38
    Fourth
    0.37
    imp
    0.37
     PPT
    0.37
    Activations Density 0.057%

    No Known Activations