© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58264
    Prev
    Next
    INDEX
    Explanations

    code structure and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     then
    -1.88
     This
    -1.80
    or
    -1.71
    al
    -1.69
    i
    -1.66
     garnered
    -1.66
     repeatedly
    -1.60
     especially
    -1.59
     possibly
    -1.57
     fanno
    -1.57
    POSITIVE LOGITS
     consci
    1.62
     письмо
    1.59
     incomparable
    1.56
    tling
    1.55
     ortodo
    1.55
     Ocak
    1.53
    皞
    1.52
    讥
    1.52
     muñ
    1.51
     Biblia
    1.51
    Activations Density 0.071%

    No Known Activations