© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14267
    Prev
    Next
    INDEX
    Explanations

    Year Limited

    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_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
    ხვევ
    1.17
     من
    1.14
    partitions
    1.12
    ನಲ್ಲಿ
    1.12
    dab
    1.10
    킷
    1.10
     সাম্রাজ
    1.09
    〝
    1.09
    ech
    1.08
    áž
    1.08
    POSITIVE LOGITS
    जीवन
    1.21
    𝙤
    1.19
    ড়িয়ে
    1.18
     tratan
    1.15
     मुआव
    1.13
    ुभ
    1.13
     Optimized
    1.13
    ৫৪
    1.13
     Ellen
    1.13
     Optimize
    1.13
    Activations Density 0.000%

    No Known Activations