© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 85547
    Prev
    Next
    INDEX
    Explanations

    user inputs for prompts

    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
    ，
    0.50
     kite
    0.48
    炎症
    0.46
    遺
    0.45
     vineyard
    0.45
     juicy
    0.45
     retroactive
    0.45
     tett
    0.44
     white
    0.43
     accessible
    0.43
    POSITIVE LOGITS
    CODES
    0.59
     funcionamiento
    0.57
     Calcula
    0.56
     Codes
    0.55
    码
    0.55
    art
    0.55
     Crater
    0.55
    Console
    0.54
     Hasta
    0.54
    ودي
    0.54
    Activations Density 0.112%

    No Known Activations