© 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. 5999
    Prev
    Next
    INDEX
    Explanations

    for specific use cases

    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
    v
    0.59
    in
    0.59
    bile
    0.55
    physiological
    0.52
    usus
    0.52
    inä
    0.52
    tol
    0.52
    Ly
    0.52
    numer
    0.52
    bil
    0.51
    POSITIVE LOGITS
     shooter
    0.51
    ಗಾರ
    0.48
     Site
    0.47
     Waldo
    0.47
     ۾
    0.46
     beim
    0.46
     withered
    0.45
    ットフォーム
    0.45
     knife
    0.44
     là
    0.44
    Activations Density 0.001%

    No Known Activations