© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10679
    Prev
    Next
    INDEX
    Explanations

    depends on

    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
    われた
    2.47
     сообще
    2.43
    ль
    2.43
    Ӏо
    2.36
    𝗁
    2.32
    டம்
    2.20
    حه
    2.12
     RUN
    2.07
    uture
    2.07
    കും
    2.04
    POSITIVE LOGITS
    likle
    3.10
    偎
    2.82
    শীল
    2.79
    ારીખ
    2.70
    seys
    2.56
    iedy
    2.54
    據
    2.51
    rivation
    2.47
    ently
    2.46
    இவ்வாறு
    2.40
    Activations Density 0.434%

    No Known Activations