© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1941
    Prev
    Next
    INDEX
    Explanations

    languages and technology scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     Breakdown
    0.99
     ر
    0.95
     Depart
    0.91
     BREAK
    0.91
     بال
    0.87
     ро
    0.86
     favorable
    0.85
     diminishing
    0.85
     ب
    0.84
     भ
    0.83
    POSITIVE LOGITS
    utils
    1.63
    アプリ
    1.53
    ソフトウェア
    1.48
    api
    1.47
    apps
    1.43
    应用程序
    1.42
    アプリケーション
    1.36
    imedia
    1.35
    analytics
    1.35
     logiciel
    1.35
    Activations Density 0.508%

    No Known Activations