© 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. 18035
    Prev
    Next
    INDEX
    Explanations

    code structure separators

    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
     gastritis
    0.38
     돼요
    0.38
     kidding
    0.37
     ajo
    0.37
     good
    0.36
     ا
    0.36
     LAMP
    0.36
     vlak
    0.35
    ോ
    0.35
     watermelon
    0.34
    POSITIVE LOGITS
    uint
    0.39
    Shared
    0.38
    Log
    0.37
    गरण
    0.37
    including
    0.37
    okość
    0.36
    DispatchRequest
    0.36
    Trashed
    0.36
    generalized
    0.36
    unified
    0.35
    Activations Density 0.038%

    No Known Activations