© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8317
    Prev
    Next
    INDEX
    Explanations

    French place names

    np_acts-logits-general · gemini-2.5-flash-lite

    clear and decreased medical terms

    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_40_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
     दिलाने
    0.47
    [/
    0.44
    [
    0.39
    Mic
    0.38
     Piy
    0.38
    턱
    0.36
    द्रोह
    0.36
     Slack
    0.36
     لگانے
    0.36
    Trend
    0.35
    POSITIVE LOGITS
     extras
    0.49
     экстра
    0.48
     हृदय
    0.45
    💛
    0.43
    lijke
    0.43
     женщина
    0.42
     inqu
    0.41
     radionuclides
    0.41
     myocardium
    0.41
     Extras
    0.40
    Activations Density 0.010%

    No Known Activations