© 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. 14110
    Prev
    Next
    INDEX
    Explanations

    constructive approaches

    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
     generative
    1.19
     用于
    1.18
     인정
    1.17
    avacanam
    1.17
     진짜
    1.16
     언급
    1.14
     這個
    1.14
    ᱲ
    1.13
     확인
    1.13
    这类
    1.13
    POSITIVE LOGITS
    ियो
    1.08
    Chevrolet
    0.98
    кою
    0.98
    Lets
    0.97
     الساعه
    0.97
    Senator
    0.96
    میل
    0.95
    किंग
    0.95
     abond
    0.94
    Organization
    0.94
    Activations Density 19.389%

    No Known Activations