© 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-262K
    7. 2601
    Prev
    Next
    INDEX
    Explanations

    drywall or wall construction

    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_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
     smartwatch
    1.05
    สมัคร
    0.88
    齿
    0.87
     phiên
    0.85
     Arabidopsis
    0.83
     турни
    0.80
     Informatics
    0.79
     République
    0.77
     gep
    0.77
    タク
    0.76
    POSITIVE LOGITS
     drywall
    2.12
     wall
    1.89
     walls
    1.89
     plaster
    1.80
    墙
    1.56
     dinding
    1.55
    walls
    1.54
     gypsum
    1.52
     دیوار
    1.51
     Walls
    1.50
    Activations Density 0.137%

    No Known Activations