© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208834
    Prev
    Next
    INDEX
    Explanations

    Parker County

    np_acts-logits-general · gemini-2.5-flash-lite

    distinct objects or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    家庭
    0.46
     Qué
    0.46
    Ꮅ
    0.46
     ಖರೀ
    0.45
    参考に
    0.45
     बिंद
    0.45
    藤
    0.44
     painfully
    0.44
    اك
    0.44
    西哥
    0.44
    POSITIVE LOGITS
     စ
    0.46
    ut
    0.46
    cps
    0.45
     permitted
    0.43
     autocl
    0.43
     compose
    0.43
     oleh
    0.43
    সত্য
    0.41
     Stewardship
    0.41
    Entry
    0.41
    Activations Density 0.000%

    No Known Activations