© 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. 31-GEMMASCOPE-2-RES-262K
    7. 199252
    Prev
    Next
    INDEX
    Explanations

    in practice, often used synonymously

    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_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
    Ω
    0.46
    Hannah
    0.46
    چھ
    0.42
    บ้าน
    0.42
    >'
    0.42
    Booking
    0.42
    >≤</
    0.42
    เล
    0.42
    Sarah
    0.42
    スタイル
    0.42
    POSITIVE LOGITS
     हरकत
    0.45
     inserting
    0.44
     вмеша
    0.44
     técn
    0.43
    ěř
    0.42
    ર્ડ
    0.40
     dụ
    0.40
    ச்ச
    0.40
     máscara
    0.39
    фици
    0.38
    Activations Density 0.001%

    No Known Activations