© 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. 248082
    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
     '
    0.46
    ,
    0.46
    sal
    0.45
    ol
    0.44
    LON
    0.44
    ע
    0.44
     *
    0.44
    awks
    0.44
    allowing
    0.44
    ܫ
    0.44
    POSITIVE LOGITS
    觊
    0.55
     örne
    0.51
     bất
    0.50
     ينا
    0.48
     нарушения
    0.48
     trục
    0.47
     шабло
    0.46
     mẫu
    0.44
    互联网档案馆
    0.44
     rời
    0.44
    Activations Density 0.002%

    No Known Activations