© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11515
    Prev
    Next
    INDEX
    Explanations

    leather and related materials

    np_acts-logits-general · gemini-2.5-flash-lite

    leather items and clothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     પગ
    0.50
     cupcakes
    0.49
     footprints
    0.48
     pedest
    0.48
    腳
    0.47
     Feet
    0.47
     cupcake
    0.46
     Rosal
    0.46
     moe
    0.46
     feet
    0.45
    POSITIVE LOGITS
     leather
    2.14
    Leather
    2.08
     Leather
    2.05
    leather
    2.05
    皮革
    1.77
    革
    1.73
     cuero
    1.62
    レザー
    1.60
     革
    1.55
     レザー
    1.50
    Activations Density 0.352%

    No Known Activations