© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249853
    Prev
    Next
    INDEX
    Explanations

    wee pad / flatworms / gallons of rain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Número
    0.54
     Número
    0.52
    ay
    0.50
    ان
    0.50
     त्य
    0.49
    Numero
    0.49
    ต่าง
    0.48
    د
    0.47
    瞠
    0.47
    槸
    0.47
    POSITIVE LOGITS
     welcher
    0.54
     salts
    0.52
     bee
    0.48
     barn
    0.48
     shaker
    0.46
     salt
    0.46
     boxers
    0.45
     yeast
    0.44
     plank
    0.44
    reeze
    0.44
    Activations Density 0.000%

    No Known Activations