© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6840
    Prev
    Next
    INDEX
    Explanations

    recipe serving sizes

    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_22_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
    گرام
    0.93
     permeated
    0.91
    деги
    0.87
    StateHandler
    0.87
    카오
    0.85
    险
    0.85
    capi
    0.83
    纶
    0.83
     Walla
    0.83
     Sih
    0.82
    POSITIVE LOGITS
    idlo
    1.08
    ingan
    1.05
     المنتج
    1.01
    ingen
    0.99
    कने
    0.98
     ಇದಕ್ಕೆ
    0.94
    idler
    0.92
    öffentlichung
    0.92
    idu
    0.90
     हो
    0.89
    Activations Density 0.005%

    No Known Activations