© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 228473
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     raw
    0.48
    陳
    0.47
    こと
    0.45
     sushi
    0.45
    ระ
    0.44
    取り
    0.44
    آ
    0.44
    何を
    0.43
    その
    0.43
     Laplacian
    0.42
    POSITIVE LOGITS
    arlas
    0.50
     عيد
    0.50
    ленном
    0.47
    тому
    0.47
    itie
    0.47
     первым
    0.46
    𝙡
    0.46
    REW
    0.45
    ElementException
    0.45
    TRACK
    0.45
    Activations Density 0.001%

    No Known Activations