© 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. 12964
    Prev
    Next
    INDEX
    Explanations

    birthday messages and program logic

    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
    Percentage
    1.50
    %、
    1.47
    PERCENT
    1.43
     Percentage
    1.38
     مقدار
    1.35
     percentage
    1.33
    %，
    1.33
    正規
    1.33
    %。
    1.32
    يز
    1.30
    POSITIVE LOGITS
     ambience
    1.06
     camaraderie
    1.01
     ambiance
    1.00
     exquis
    0.96
     empowerment
    0.93
     collaboration
    0.91
     ethos
    0.90
     estilo
    0.90
    rust
    0.89
    craft
    0.88
    Activations Density 0.081%

    No Known Activations