© 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-65K
    7. 27722
    Prev
    Next
    INDEX
    Explanations

    last day, you ask

    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_65k_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
     فیصلے
    0.49
    鼐
    0.48
    钀
    0.48
    领域的
    0.48
    颌
    0.47
     контек
    0.45
    䈤
    0.45
    องค์
    0.44
    叓
    0.44
    但这
    0.44
    POSITIVE LOGITS
     uso
    0.55
     use
    0.54
     tubo
    0.54
     downloading
    0.54
     used
    0.52
     tube
    0.50
     waterproof
    0.48
    re
    0.47
    lof
    0.47
    pc
    0.46
    Activations Density 0.014%

    No Known Activations