© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 85017
    Prev
    Next
    INDEX
    Explanations

    hand plane woodworking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    木
    0.46
     woodworking
    0.43
    lywood
    0.42
     sawdust
    0.42
     madera
    0.42
     plywood
    0.41
    шли
    0.40
     sanded
    0.40
    ubon
    0.40
    刻
    0.39
    POSITIVE LOGITS
     irons
    0.47
     plane
    0.45
     horticulture
    0.45
     Plane
    0.43
     الهول
    0.42
     horticultural
    0.41
    developer
    0.41
     manually
    0.40
    Plane
    0.39
    planner
    0.39
    Activations Density 0.003%

    No Known Activations