© 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. 14765
    Prev
    Next
    INDEX
    Explanations

    with food items

    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
    𝐟
    2.16
    son
    1.96
    то
    1.95
    𝘧
    1.92
    ჰ
    1.92
    teen
    1.91
    imwrite
    1.82
    ै
    1.80
    sto
    1.79
    ნ
    1.79
    POSITIVE LOGITS
    ERTY
    2.45
     있다면
    2.06
     #[
    2.02
    iagnosed
    1.99
     onTap
    1.98
     非常
    1.96
     사항
    1.95
    。【
    1.95
     ints
    1.94
     বিষয়
    1.93
    Activations Density 0.198%

    No Known Activations