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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13318
    Prev
    Next
    INDEX
    Explanations

    defensive lines, response, and tactics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    oxidase
    1.54
     clean
    1.52
     CLEAN
    1.48
    ्यक्रम
    1.47
    ㄒ
    1.45
     Clean
    1.43
    hadoop
    1.39
    Clean
    1.37
    writeValue
    1.36
    clean
    1.35
    POSITIVE LOGITS
    inkel
    1.55
    साइट
    1.48
    ｨ
    1.46
    े
    1.38
     atti
    1.38
     nau
    1.33
    ా
    1.31
     Е
    1.30
    iveness
    1.30
     against
    1.29
    Activations Density 0.080%

    No Known Activations