© 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. 15009
    Prev
    Next
    INDEX
    Explanations

    Supporting, NOT, ignore

    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
     وت
    0.55
     שא
    0.52
     ה
    0.51
     וא
    0.50
    ।
    0.50
    /
    0.49
    ","
    0.49
     לא
    0.49
     או
    0.47
     قلت
    0.47
    POSITIVE LOGITS
     agribusiness
    0.54
     primarily
    0.48
     ГӀ
    0.44
     FRG
    0.43
     feline
    0.43
    ێکی
    0.42
     agri
    0.41
    šić
    0.41
    作业
    0.40
     polygonal
    0.40
    Activations Density 0.001%

    No Known Activations