© 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-65K
    7. 11710
    Prev
    Next
    INDEX
    Explanations

    g followed by punctuation

    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_65k_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
    ੧
    0.45
    Whoever
    0.44
     mention
    0.44
    Someone
    0.43
    næ
    0.42
    ोह
    0.41
     некоторое
    0.41
    (({
    0.41
     นาง
    0.40
    POSITIVE LOGITS
     экономической
    0.42
     để
    0.41
    ását
    0.40
     với
    0.40
     cộng
    0.40
     தயாரிக்க
    0.39
     včetně
    0.38
     تطبيقات
    0.37
     bằng
    0.37
    夯
    0.37
    Activations Density 0.013%

    No Known Activations