© 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. 7601
    Prev
    Next
    INDEX
    Explanations

    pronunciation, fuse box, quotes, install, Promise

    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
     black
    0.57
     splash
    0.53
     Middle
    0.52
     l
    0.51
     year
    0.50
     full
    0.50
     BA
    0.49
     ra
    0.48
     recruitment
    0.48
     dynamic
    0.48
    POSITIVE LOGITS
     postérieurs
    0.54
    有趣
    0.51
     sucks
    0.51
    kjhtml
    0.48
     introns
    0.47
    嫣
    0.46
    事物
    0.46
    льне
    0.45
    стям
    0.45
     econôm
    0.45
    Activations Density 0.000%

    No Known Activations