© 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. 4166
    Prev
    Next
    INDEX
    Explanations

    library of content

    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
    Negative Logits
    usters
    2.51
    د
    2.40
    satz
    2.40
    t
    2.35
     نرم
    2.32
    يح
    2.32
    NOP
    2.30
    usch
    2.29
    উন্ট
    2.23
    hibited
    2.22
    POSITIVE LOGITS
    ское
    3.02
    ১৪
    2.93
    ১০
    2.92
    ২১
    2.85
    ক্তি
    2.81
    裳
    2.77
     tailed
    2.73
    сть
    2.69
    ৪৩
    2.68
    ские
    2.68
    Activations Density 0.017%

    No Known Activations