© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8639
    Prev
    Next
    INDEX
    Explanations

    for repeating

    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_40_width_16k_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
    irken
    0.38
    <unused67>
    0.37
    COU
    0.37
     राशिफल
    0.36
    лкой
    0.36
    殃
    0.36
     произво
    0.35
    واز
    0.35
    检
    0.35
    distplot
    0.34
    POSITIVE LOGITS
     repeating
    2.95
     repeat
    2.88
     repeats
    2.84
    重复
    2.84
     repeated
    2.83
     ripet
    2.78
     repetitive
    2.75
     повторя
    2.73
     repetition
    2.70
     Repeat
    2.67
    Activations Density 0.660%

    No Known Activations