© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 143641
    Prev
    Next
    INDEX
    Explanations

    links and calls to action

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

    spirit world, deform under, sister

    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
    ڼ
    0.45
     व्यक्तित्व
    0.44
     آتا
    0.43
    ўцаў
    0.43
    FieldNumber
    0.42
    віду
    0.41
    分類
    0.41
    '।
    0.41
    äänt
    0.40
     ব্যক্তিত্ব
    0.39
    POSITIVE LOGITS
     =
    0.48
    都是
    0.43
     peter
    0.42
     t
    0.42
     BOOKS
    0.41
     встречаются
    0.41
    וא
    0.41
     vở
    0.40
     vinho
    0.40
    やか
    0.40
    Activations Density 0.001%

    No Known Activations