© 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. 6831
    Prev
    Next
    INDEX
    Explanations

    next lines, standard parts

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

    physical descriptions and specific names

    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
    ницу
    0.54
    ныя
    0.48
     olursa
    0.48
    aní
    0.47
    𝟕
    0.47
    蹑
    0.46
    𒁺
    0.46
    нули
    0.46
    Prim
    0.45
    辔
    0.45
    POSITIVE LOGITS
    o
    0.56
    و
    0.55
     photographic
    0.45
     consid
    0.45
    ो
    0.44
     Student
    0.44
    asia
    0.44
     rues
    0.44
     whistling
    0.42
     proclaimed
    0.42
    Activations Density 0.000%

    No Known Activations