© 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. 38617
    Prev
    Next
    INDEX
    Explanations

    place names and organizations

    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
     only
    -2.02
     their
    -1.82
    </td>
    -1.73
     from
    -1.65
     just
    -1.61
    ماع
    -1.45
     luka
    -1.45
     vinci
    -1.45
     not
    -1.45
     they
    -1.41
    POSITIVE LOGITS
     of
    1.95
     flir
    1.66
     anstatt
    1.59
    Или
    1.59
     السنة
    1.57
    Quieres
    1.53
     Instead
    1.52
    
    1.51
    ‚¬
    1.48
    菔
    1.48
    Activations Density 0.010%

    No Known Activations