© 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. 38165
    Prev
    Next
    INDEX
    Explanations

    foreign language and group identifiers

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

    setup considerations

    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
    不仅
    0.40
     демонстри
    0.37
    实
    0.36
    作为
    0.36
    与
    0.36
    🕵
    0.35
    有着
    0.35
    我们
    0.35
     очередной
    0.35
    对于
    0.35
    POSITIVE LOGITS
     فرنسا
    0.32
     كلهم
    0.32
     ఎక్కువ
    0.31
     پیسې
    0.31
     drugih
    0.30
     بالٹ
    0.30
     मुसलमान
    0.29
     antal
    0.29
     Jews
    0.29
    这些人
    0.29
    Activations Density 0.320%

    No Known Activations