© 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. 98755
    Prev
    Next
    INDEX
    Explanations

    phone numbers and dates

    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
     bijzondere
    -1.76
     ujedno
    -1.75
     creó
    -1.68
    ündig
    -1.62
     enfati
    -1.61
     sostener
    -1.60
     vijf
    -1.57
     akumulator
    -1.57
     sposob
    -1.55
     rése
    -1.55
    POSITIVE LOGITS
    6
    2.70
    9
    2.64
    7
    2.63
    4
    2.56
    1
    2.52
    8
    2.42
    2
    2.38
    3
    2.38
    5
    2.33
    ’
    2.11
    Activations Density 0.017%

    No Known Activations