© 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. 7-GEMMASCOPE-2-RES-16K
    7. 4094
    Prev
    Next
    INDEX
    Explanations

    egg dishes

    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_7_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
    ourier
    2.68
    hz
    2.57
    ྫ
    2.57
    ባል
    2.36
     abges
    2.33
     PROVIDED
    2.33
     elevada
    2.28
    فع
    2.24
     Borders
    2.23
    LayoutStyle
    2.22
    POSITIVE LOGITS
     yolks
    2.83
    lat
    2.72
    ikä
    2.66
    regator
    2.60
     hern
    2.50
    Egg
    2.44
     hh
    2.41
    اعه
    2.40
    氨
    2.33
    نف
    2.25
    Activations Density 0.042%

    No Known Activations