© 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. 6932
    Prev
    Next
    INDEX
    Explanations

    data structures and manipulation

    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
    ERCE
    2.03
    terior
    1.96
    啬
    1.95
     oldCount
    1.90
    ANCE
    1.85
    стви
    1.80
    ності
    1.79
    szön
    1.79
     emboss
    1.79
    өө
    1.78
    POSITIVE LOGITS
    affected
    1.72
    <thead>
    1.60
    <tbody>
    1.54
    involved
    1.52
    GridView
    1.47
    points
    1.44
    isable
    1.43
    ilers
    1.41
     points
    1.40
    pray
    1.36
    Activations Density 0.048%

    No Known Activations