Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 119547
    Prev
    Next
    INDEX
    Explanations

    sorting with key

    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
     mW
    0.44
     프로
    0.40
     sot
    0.39
    絫
    0.39
     स्टेप
    0.39
    Editor
    0.38
    urezza
    0.38
    紫外
    0.38
     EDITOR
    0.38
    সিং
    0.37
    POSITIVE LOGITS
    زل
    0.41
    greSQL
    0.37
    signOut
    0.37
    oarthritis
    0.36
    statement
    0.36
    ناصر
    0.36
    ⑮
    0.35
    drain
    0.35
     बिंदुओं
    0.35
    getinfo
    0.35
    Activations Density 0.001%

    No Known Activations