© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 10027
    Prev
    Next
    INDEX
    Explanations

    Usage followed by colon

    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_65k_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
     gotta
    0.46
    我们要
    0.44
    苒
    0.41
     melhores
    0.38
     کنیم
    0.38
    更好地
    0.38
    我們要
    0.38
     Fam
    0.38
     আখ্যা
    0.38
     glorious
    0.38
    POSITIVE LOGITS
    roveň
    0.45
     మరియు
    0.43
     ۽
    0.42
    ಿರುವ
    0.42
     ಮತ್ತು
    0.41
    धानिक
    0.40
     selepas
    0.39
     thiab
    0.38
     indemnity
    0.38
     unenforceable
    0.38
    Activations Density 0.055%

    No Known Activations