© 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. 15680
    Prev
    Next
    INDEX
    Explanations

    occupations and job duties

    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
     from
    -1.85
     only
    -1.70
     on
    -1.62
     their
    -1.59
     by
    -1.58
     the
    -1.46
     this
    -1.35
     they
    -1.34
     will
    -1.34
     all
    -1.30
    POSITIVE LOGITS
    ୨
    1.49
     véhic
    1.49
     réfrig
    1.48
     работе
    1.33
     work
    1.31
    atów
    1.30
    ⏪
    1.27
    dengan
    1.24
     práci
    1.23
     závis
    1.23
    Activations Density 0.109%

    No Known Activations