© 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. 40-GEMMASCOPE-2-RES-262K
    7. 5351
    Prev
    Next
    INDEX
    Explanations

    comparison tables and features

    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_40_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
     ◆
    0.37
     ♦
    0.34
    ignés
    0.34
    argc
    0.34
     ////
    0.34
    سط
    0.33
    льнявыя
    0.33
    ↵↵↵↵↵↵↵↵↵↵
    0.32
    ‖</
    0.32
     ＊
    0.32
    POSITIVE LOGITS
    :
    0.32
    --------------
    0.29
    ----------------
    0.29
    0.29
    k
    0.29
    jet
    0.29
     trusted
    0.29
    -------------
    0.29
    bal
    0.29
    M
    0.29
    Activations Density 0.013%

    No Known Activations