© 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. 53357
    Prev
    Next
    INDEX
    Explanations

    find the

    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
     您
    0.46
     باستخدام
    0.42
     நன்க
    0.42
    take
    0.40
     ayrıca
    0.40
    sächlich
    0.40
    accessed
    0.40
     Ayrıca
    0.39
    为您
    0.39
     ஊக்கு
    0.39
    POSITIVE LOGITS
    س
    0.46
    pèce
    0.46
     gentle
    0.46
    ੜ
    0.44
    ರೀಕ್ಷ
    0.44
    ਹ
    0.44
     peak
    0.44
    ጣት
    0.43
    ੱਖ
    0.43
    ह
    0.43
    Activations Density 0.002%

    No Known Activations