© 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. 200300
    Prev
    Next
    INDEX
    Explanations

    ethical, moral, travel, forcing

    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
    ي
    0.55
    م
    0.54
    י
    0.52
     imprimir
    0.50
    м
    0.48
     quando
    0.47
     su
    0.47
    .
    0.46
     cuando
    0.46
     qualify
    0.45
    POSITIVE LOGITS
    Czechoslovakia
    0.48
     हमलों
    0.48
     مداخل
    0.48
    疥
    0.48
    KCl
    0.47
    Stocks
    0.46
    젤
    0.46
    지지
    0.45
    Sunflower
    0.45
    쐐
    0.44
    Activations Density 0.001%

    No Known Activations