© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22575
    Prev
    Next
    INDEX
    Explanations

    related fields, items, or duties

    np_acts-logits-general · gemini-2.5-flash-lite

    relevant experiences, data, studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一個
    0.84
    大
    0.78
    大脑
    0.73
    ಲ
    0.71
     هوا
    0.70
    一个
    0.69
    美食
    0.66
    ä
    0.66
     potenti
    0.65
    手臂
    0.64
    POSITIVE LOGITS
    IN
    0.96
     terkait
    0.96
    )
    0.88
    र्स
    0.85
    Related
    0.82
    相关的
    0.79
    kę
    0.79
    س
    0.79
    де
    0.78
     relacionados
    0.77
    Activations Density 0.031%

    No Known Activations