© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    already has

    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
     Á
    1.45
     ré
    1.42
    Á
    1.40
     chân
    1.40
     difesa
    1.38
     atenção
    1.34
     ближай
    1.33
     dio
    1.26
     Plata
    1.26
     między
    1.26
    POSITIVE LOGITS
    foresaid
    2.14
     pertaining
    2.06
    ivasena
    2.06
    incerely
    1.92
    iotic
    1.88
    avings
    1.86
    <unused298>
    1.85
    ບບ
    1.83
     impede
    1.83
    ethod
    1.82
    Activations Density 0.424%

    No Known Activations