© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9080
    Prev
    Next
    INDEX
    Explanations

    bread, dough, and baking ingredients

    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_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SNR
    1.12
     SRI
    1.12
    邵
    1.09
     Vargas
    1.05
     IPS
    1.02
     Whitley
    1.01
    溆
    0.97
     Fairchild
    0.96
    SNR
    0.95
     잔
    0.95
    POSITIVE LOGITS
     dough
    1.80
     bakers
    1.70
     loaves
    1.70
     breads
    1.69
     sourdough
    1.69
     bread
    1.68
     baker
    1.61
     bakery
    1.59
     Bread
    1.59
     Dough
    1.57
    Activations Density 0.432%

    No Known Activations