© 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. 5868
    Prev
    Next
    INDEX
    Explanations

    locations, activities, and things

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

    interactivity, features, and strategy

    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
     amerikanischen
    0.34
     frau
    0.33
    㷌
    0.32
     солдат
    0.31
     ถ้า
    0.31
     व्यापारी
    0.29
     bakın
    0.29
    잌
    0.29
     banco
    0.29
    тири
    0.29
    POSITIVE LOGITS
    ↵↵
    0.43
    1
    0.36
     and
    0.34
    ',
    0.32
    ,
    0.32
     etc
    0.31
    core
    0.31
    V
    0.30
    c
    0.30
    ul
    0.30
    Activations Density 0.271%

    No Known Activations