© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2881
    Prev
    Next
    INDEX
    Explanations

    Wilkerson, Oppenheimer, operating systems

    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_7_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
    e
    1.92
    mathrm
    1.78
    t
    1.75
    dependent
    1.69
    s
    1.63
    abeled
    1.63
    in
    1.62
    ds
    1.61
    groups
    1.57
    tric
    1.57
    POSITIVE LOGITS
     pok
    1.83
     paz
    1.77
     bata
    1.77
     tremor
    1.72
     yath
    1.68
    葚
    1.67
     raz
    1.62
     venge
    1.62
     loft
    1.62
     hernia
    1.61
    Activations Density 0.000%

    No Known Activations