© 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. 7215
    Prev
    Next
    INDEX
    Explanations

    function validation

    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
     lower
    1.35
     level
    1.32
    원이
    1.31
    ر
    1.30
     non
    1.28
     heavy
    1.27
     fly
    1.27
     되지
    1.26
    м
    1.25
     spend
    1.25
    POSITIVE LOGITS
    thet
    1.86
    sw
    1.86
    tof
    1.83
     इनकार
    1.73
    Samp
    1.72
    apiKey
    1.71
    cv
    1.70
    ामान्य
    1.69
    arrayOf
    1.68
    cb
    1.67
    Activations Density 0.002%

    No Known Activations