© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46287
    Prev
    Next
    INDEX
    Explanations

    Attributing everything to chance

    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
    の
    0.48
     Compañ
    0.46
    ‌ترین
    0.46
     instance
    0.45
     Fonction
    0.45
    贏
    0.44
    uées
    0.43
     ответствен
    0.42
     يت
    0.42
     examin
    0.42
    POSITIVE LOGITS
    र
    0.57
    ک
    0.55
    ক
    0.52
    ד
    0.48
    𝘳
    0.47
    𝙎
    0.45
     PUBLIC
    0.45
    orderEntry
    0.45
    ᒃ
    0.45
    sai
    0.44
    Activations Density 0.003%

    No Known Activations