© 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. 14013
    Prev
    Next
    INDEX
    Explanations

    against the windows

    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
     ONLY
    1.05
    Duplicates
    1.04
    duplicates
    1.03
     confund
    1.02
     only
    1.01
    酱
    1.00
    éna
    0.99
    Pune
    0.97
    <unused1038>
    0.97
     Mysore
    0.97
    POSITIVE LOGITS
     фізи
    0.91
    ப்பிய
    0.81
    道の
    0.80
     धरती
    0.80
     Metric
    0.80
     ਆ
    0.80
    ріа
    0.79
     Orbit
    0.79
    stände
    0.78
    eria
    0.78
    Activations Density 0.379%

    No Known Activations