© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 64398
    Prev
    Next
    INDEX
    Explanations

    discrete problem and selection

    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_all/layer_41_width_262k_l0_big
    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
    ג
    0.54
    Вели
    0.53
     특
    0.51
    譁
    0.49
     ק
    0.49
    ייס
    0.49
     מלא
    0.49
     아름
    0.49
     Оста
    0.48
    지난
    0.48
    POSITIVE LOGITS
     nearby
    0.46
     copy
    0.45
     neighboring
    0.43
     coincident
    0.43
     matching
    0.42
     colleague
    0.40
     wiederum
    0.40
     candidate
    0.39
     y
    0.39
     whom
    0.38
    Activations Density 0.001%

    No Known Activations