© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12892
    Prev
    Next
    INDEX
    Explanations

    century United States doing consequences aumentada pandas

    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_13_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
     generous
    1.45
    𝑐
    1.24
     mouse
    1.21
     negligible
    1.21
    chid
    1.21
     mice
    1.20
     dumb
    1.20
    rä
    1.17
     travel
    1.17
     ID
    1.15
    POSITIVE LOGITS
    (":")[
    1.22
    ([(
    1.22
    }"
    1.22
    "},
    1.21
     lehet
    1.18
    ":{"
    1.16
    之前的
    1.16
    ֙
    1.15
    重心
    1.14
     координаты
    1.14
    Activations Density 0.000%

    No Known Activations