© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 12509
    Prev
    Next
    INDEX
    Explanations

    dialogue starters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    Tokens that appear at the beginning of the model's response or mark transitions between different parts of the response structure, including acknowledgments, formatting elements, role-play indicators, and the start of actual content delivery. These tokens signal the model's engagement with unusual, creative, or instruction-following tasks that deviate from standard question-answering.

    eleuther_acts_top20 · claude-4-5-sonnetTriggered by @jamesnaruto04
    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
    5
    0.29
    8
    0.29
    deki
    0.29
     twor
    0.29
     darbo
    0.29
     pristup
    0.28
     gerenci
    0.28
     workflow
    0.27
    重視
    0.27
     instructive
    0.27
    POSITIVE LOGITS
     Button
    0.30
     Merriam
    0.30
     Kimberly
    0.30
    ampton
    0.29
     маленький
    0.28
     Bethany
    0.27
     неожидан
    0.27
    ână
    0.27
     Australian
    0.27
    改变
    0.27
    Activations Density 0.700%

    No Known Activations