© 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-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15714
    Prev
    Next
    INDEX
    Explanations

    colors and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     Gandh
    0.63
     பெற்றோ
    0.58
    有了
    0.57
     Beverages
    0.57
    \/}
    0.55
     extensión
    0.55
     बेटर
    0.54
     விரிவா
    0.54
    圿
    0.52
     বিমানবন্দরে
    0.52
    POSITIVE LOGITS
    緑
    0.80
     accentuate
    0.77
    rgba
    0.73
    灰色
    0.70
     teal
    0.69
     rgba
    0.66
    seagreen
    0.65
     color
    0.63
    RGB
    0.63
    Accent
    0.63
    Activations Density 0.002%

    No Known Activations