© 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. 14822
    Prev
    Next
    INDEX
    Explanations

    function return values and parameters

    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
    系統
    1.13
     ك
    1.06
     k
    1.05
    rog
    1.05
     completely
    1.05
     Al
    1.04
     co
    1.03
    oster
    1.01
    <0xB5>
    1.00
     that
    1.00
    POSITIVE LOGITS
     méridionale
    2.04
     ersche
    1.75
    šť
    1.71
     abiertas
    1.71
     imprend
    1.69
    <unused285>
    1.67
     azure
    1.66
     souver
    1.65
     universidades
    1.64
     ciências
    1.61
    Activations Density 0.001%

    No Known Activations