© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138004
    Prev
    Next
    INDEX
    Explanations

    technical terms and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nominally
    0.44
     சுர
    0.43
     faintly
    0.42
     ウォ
    0.41
     අව
    0.41
     inserting
    0.40
     unwelcome
    0.40
    ﾒ
    0.40
     ಟ
    0.39
     peripher
    0.38
    POSITIVE LOGITS
    เหมือน
    0.52
    তাকে
    0.48
    렸
    0.47
    Эта
    0.45
    หมือน
    0.45
    乐队
    0.44
    滈
    0.44
    ্বেও
    0.44
    >().
    0.44
    였습니다
    0.43
    Activations Density 0.005%

    No Known Activations