© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2408
    Prev
    Next
    INDEX
    Explanations

    honoring or showing respect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    岖
    2.28
    د
    2.05
    ीय
    1.81
    tweets
    1.77
    ร์
    1.72
    hello
    1.70
    いろいろ
    1.70
    swith
    1.67
    ture
    1.67
    蚪
    1.66
    POSITIVE LOGITS
    ε
    2.27
    ▪
    1.95
    ার
    1.85
    ан
    1.84
    ্স
    1.79
     giản
    1.67
    ব্রত
    1.67
     pastime
    1.66
    ко
    1.63
    ably
    1.63
    Activations Density 0.012%

    No Known Activations