© 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. 13295
    Prev
    Next
    INDEX
    Explanations

    plotting labels and colors

    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
    ᴍ
    1.87
    ﺤ
    1.76
    -"+
    1.70
     Er
    1.69
    ING
    1.65
    ﺗ
    1.65
    ﺒ
    1.63
    Er
    1.62
    BOT
    1.60
    -
    1.60
    POSITIVE LOGITS
     keduanya
    1.60
    ঙ্গা
    1.54
    ่
    1.51
    cope
    1.43
    द्धांत
    1.42
    श्त
    1.35
    thiophene
    1.33
    هو
    1.32
    циа
    1.29
     anillos
    1.29
    Activations Density 0.106%

    No Known Activations