© 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. 40-GEMMASCOPE-2-RES-262K
    7. 9526
    Prev
    Next
    INDEX
    Explanations

    3

    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_40_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
     نیچے
    0.51
    ƾ
    0.46
    پرس
    0.46
    ক্রিয়
    0.45
    ്യൂ
    0.45
    िटी
    0.44
    الہ
    0.44
    inę
    0.43
    ıyoruz
    0.42
     ہُ
    0.42
    POSITIVE LOGITS
    3
    0.61
    th
    0.51
     intentions
    0.47
     i
    0.47
     b
    0.46
    ри
    0.46
    aca
    0.46
    d
    0.45
     u
    0.45
    re
    0.45
    Activations Density 0.015%

    No Known Activations