© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123472
    Prev
    Next
    INDEX
    Explanations

    function definitions and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '"
    0.42
     энерги
    0.39
    ächlich
    0.39
    dotnet
    0.39
    ""
    0.38
    誨
    0.36
     deb
    0.36
    ளின்
    0.35
    (_.
    0.35
    чика
    0.35
    POSITIVE LOGITS
    હા
    0.46
     studenti
    0.45
     posso
    0.45
    í
    0.45
    ري
    0.45
    ціона
    0.44
    ëve
    0.44
    versed
    0.43
     युग
    0.43
    ഗ്യ
    0.43
    Activations Density 0.001%

    No Known Activations