© 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. 10283
    Prev
    Next
    INDEX
    Explanations

    ASCII art generation

    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
    𝐞
    2.88
    𝐚
    2.67
    থেষ্ট
    2.59
    𝐡
    2.58
     انگیز
    2.52
    𝐨
    2.44
     পড়ে
    2.40
    &\
    2.39
    𝐲
    2.39
    宗旨
    2.37
    POSITIVE LOGITS
    gle
    3.10
    den
    2.94
    ا
    2.89
    ean
    2.83
    ी
    2.74
    y
    2.71
    dyn
    2.66
    া
    2.63
    inium
    2.60
    nements
    2.60
    Activations Density 0.016%

    No Known Activations