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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 8974
    Prev
    Next
    INDEX
    Explanations

    weaving and textiles

    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_17_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
     inorganic
    1.19
    眼鏡
    1.17
    ষ্ক
    1.17
    لن
    1.16
     tuổi
    1.15
    ب
    1.13
    ▀
    1.11
    Ҭ
    1.08
    дың
    1.07
     зака
    1.05
    POSITIVE LOGITS
    🧶
    2.01
     threads
    1.97
     yarn
    1.86
     yarns
    1.85
     textile
    1.84
     Textile
    1.81
     stitches
    1.80
     weave
    1.79
     wool
    1.79
     carpets
    1.77
    Activations Density 0.220%

    No Known Activations