© 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. 13615
    Prev
    Next
    INDEX
    Explanations

    lists and sections

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

    detecting, using, controlling, managing

    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
    ่
    0.42
    Анд
    0.42
    訾
    0.41
    Ꮔ
    0.39
    貳
    0.39
    ௭
    0.38
    ੪
    0.38
     inconn
    0.38
    骊
    0.38
    戏剧
    0.38
    POSITIVE LOGITS
    0.41
     you
    0.38
     using
    0.38
    ”,
    0.38
     Use
    0.38
    ’,
    0.38
     |
    0.37
     your
    0.36
    iling
    0.36
     use
    0.36
    Activations Density 0.066%

    No Known Activations