© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6555
    Prev
    Next
    INDEX
    Explanations

    grass and lawn vegetation

    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
    Negative Logits
    瓮
    1.13
    鞆
    1.11
    闽
    1.08
    甕
    1.04
     jars
    1.03
     carapace
    1.02
    cave
    1.01
    雫
    1.00
     cave
    0.99
    槨
    0.99
    POSITIVE LOGITS
     grass
    2.02
     grasses
    2.00
     Grass
    1.99
    grass
    1.94
    Grass
    1.90
     grassy
    1.52
     grasslands
    1.46
     Gras
    1.43
     grassland
    1.43
    草
    1.42
    Activations Density 0.182%

    No Known Activations