© 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. 19977
    Prev
    Next
    INDEX
    Explanations

    import React

    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
    K
    0.55
    き
    0.54
    ها
    0.54
    टाम
    0.53
    protein
    0.50
    ยนต์
    0.50
    inė
    0.49
    いる
    0.48
    एस
    0.48
    ുവരി
    0.47
    POSITIVE LOGITS
    től
    0.64
    tól
    0.57
    t
    0.50
     from
    0.49
     ହ
    0.48
     imgSrc
    0.48
     từ
    0.47
     忄
    0.45
     از
    0.45
    u
    0.45
    Activations Density 0.020%

    No Known Activations