© 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. 7701
    Prev
    Next
    INDEX
    Explanations

    biological terms and concepts

    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
    <bos>
    1.74
    枨
    1.62
    mania
    1.57
     Motorsports
    1.54
    BackPressed
    1.51
    obbies
    1.51
    disco
    1.50
    CLA
    1.49
     Hakim
    1.48
     glfw
    1.45
    POSITIVE LOGITS
    즙
    1.63
    कलन
    1.62
    iall
    1.60
    գ
    1.51
    Tissue
    1.47
     tissue
    1.47
    äär
    1.46
    leukin
    1.45
    ర్ణ
    1.45
    те
    1.44
    Activations Density 0.328%

    No Known Activations