© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7865
    Prev
    Next
    INDEX
    Explanations

    /wiki/ url segments

    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_22_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
    的
    4.99
    ের
    4.89
    の
    4.79
    의
    4.30
    ı
    3.47
    ों
    3.31
    的具体
    2.90
    的表现
    2.68
    的数量
    2.66
    ის
    2.63
    POSITIVE LOGITS
    忡
    1.30
     گے
    1.27
    ‌ನ
    1.23
    ‌ನಲ್ಲಿ
    1.21
     گے۔
    1.19
    તમ
    1.11
     último
    1.08
    ۰۰
    1.08
    Last
    1.04
     dernière
    1.04
    Activations Density 0.020%

    No Known Activations