© 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. 16-GEMMASCOPE-2-RES-16K
    7. 606
    Prev
    Next
    INDEX
    Explanations

    half of

    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_16_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
    ו
    0.59
    V
    0.53
    Danke
    0.52
    T
    0.52
    Superhero
    0.50
    Wet
    0.50
    GYPT
    0.49
    AndDelete
    0.49
    ק
    0.48
    X
    0.48
    POSITIVE LOGITS
    τα
    0.67
    padă
    0.57
     of
    0.55
    し
    0.54
    ayutt
    0.54
     brimming
    0.53
    äksi
    0.52
    ід
    0.52
    è
    0.50
    说到
    0.50
    Activations Density 12.819%

    No Known Activations