© 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. 22-GEMMASCOPE-RES-131K
    7. 25063
    Prev
    Next
    INDEX
    Explanations

    java/c++ imports

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    鶺
    -1.50
     escote
    -1.48
     manualidades
    -1.45
     laiton
    -1.39
     magasiner
    -1.39
    さぁ
    -1.36
     excès
    -1.36
     extré
    -1.36
     tunik
    -1.34
     ekolog
    -1.34
    POSITIVE LOGITS
    n
    1.73
    i
    1.64
    p
    1.63
    u
    1.62
    b
    1.61
    g
    1.55
    d
    1.49
    j
    1.48
    te
    1.48
    er
    1.48
    Activations Density 0.009%

    No Known Activations