© 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. 13462
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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
    揊
    0.44
    ন
    0.43
     harte
    0.41
    药
    0.41
     Tokio
    0.40
     Mädchen
    0.40
    cyclopent
    0.39
    ⴽ
    0.39
    habilit
    0.39
     ط
    0.39
    POSITIVE LOGITS
    nd
    0.58
    एं
    0.49
     consiste
    0.39
    anh
    0.39
    esh
    0.39
     सकेगा
    0.38
    2
    0.38
    ούς
    0.37
    ING
    0.37
    ndal
    0.37
    Activations Density 0.012%

    No Known Activations