© 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. 2716
    Prev
    Next
    INDEX
    Explanations

    innovation and ideology

    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
    nya
    5.49
    了
    5.48
    اً
    4.70
    self
    4.34
    n
    4.27
    க்
    4.24
    ly
    3.95
    li
    3.95
    다고
    3.91
    k
    3.86
    POSITIVE LOGITS
    ে
    5.04
    a
    4.50
    e
    4.48
    ein
    4.02
    aaaaaaaa
    3.95
    า
    3.93
    aaaa
    3.91
    ńska
    3.87
    উন্ট
    3.81
    vertine
    3.71
    Activations Density 0.850%

    No Known Activations