© 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. 16-GEMMASCOPE-2-RES-262K
    7. 137953
    Prev
    Next
    INDEX
    Explanations

    in the

    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_16_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
    지
    0.84
    (
    0.82
    ب
    0.78
    ك
    0.73
     (
    0.71
    {
    0.67
    ف
    0.63
    گی
    0.62
    ق
    0.61
    دا
    0.60
    POSITIVE LOGITS
     membres
    0.72
     član
    0.71
     футболдук
    0.70
     membre
    0.68
    Bechyné
    0.65
     tiež
    0.64
    FindingsResponse
    0.64
     onDelete
    0.63
    PolicyQuery
    0.63
     starost
    0.63
    Activations Density 0.079%

    No Known Activations