© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7414
    Prev
    Next
    INDEX
    Explanations

    code block starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    aii
    0.73
    ”:
    0.69
    ”,
    0.66
    !”,
    0.66
    ?”,
    0.66
    xaxis
    0.64
    ((-
    0.64
    imagens
    0.64
    \":
    0.64
    ","-
    0.63
    POSITIVE LOGITS
    дентифика
    0.84
     *\
    0.83
     测试
    0.81
     attainment
    0.77
     testclass
    0.76
     ক্ষত্রিয়
    0.76
     charity
    0.76
     characterizes
    0.76
     African
    0.76
    素晴らしい
    0.76
    Activations Density 0.022%

    No Known Activations