© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7100
    Prev
    Next
    INDEX
    Explanations

    vegetables and eco-friendly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     optically
    1.36
    KEY
    1.35
    osecond
    1.32
     key
    1.31
     Key
    1.31
    ault
    1.31
    ️
    1.31
    cích
    1.30
     Igor
    1.25
     dessus
    1.24
    POSITIVE LOGITS
    forestry
    1.83
    ambiental
    1.76
    ivorous
    1.72
    বিনোদন
    1.68
     環
    1.59
     Ordnung
    1.58
    晚餐
    1.54
    ivores
    1.48
    FundMe
    1.48
    ytuc
    1.46
    Activations Density 0.136%

    No Known Activations