© 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. 13326
    Prev
    Next
    INDEX
    Explanations

    food and other topics

    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
     diners
    2.24
     dripping
    2.03
     splashing
    2.01
     naut
    1.98
     diner
    1.97
     tableware
    1.88
    !/"
    1.87
     raffin
    1.86
     gastronom
    1.82
     bland
    1.80
    POSITIVE LOGITS
    ా
    1.75
    త్మ
    1.66
    site
    1.59
    lom
    1.57
    iczna
    1.56
    жда
    1.54
    лат
    1.54
    cribes
    1.53
    icz
    1.52
    sen
    1.49
    Activations Density 0.098%

    No Known Activations