© 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. 22582
    Prev
    Next
    INDEX
    Explanations

    digits followed by punctuation or 'in'

    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
    Not in Any Lists

    No Comments

    Negative Logits
     each
    -1.66
     costumi
    -1.50
     fiecare
    -1.45
     видит
    -1.45
     sayfası
    -1.44
    Karakter
    -1.42
     voleva
    -1.41
     ulei
    -1.41
     viata
    -1.40
    leriyle
    -1.39
    POSITIVE LOGITS
     of
    2.83
     that
    1.83
     этой
    1.63
     for
    1.61
     этого
    1.52
     „
    1.49
    ↵↵
    1.47
     этих
    1.41
    ↵
    1.39
     dieses
    1.38
    Activations Density 0.215%

    No Known Activations