© 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. 38406
    Prev
    Next
    INDEX
    Explanations

    `ham` within words

    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
     trámites
    -3.27
     empleos
    -3.02
    鶿
    -2.91
     tocado
    -2.86
     ziyaretçi
    -2.86
     deberes
    -2.81
    瑧
    -2.80
    铪
    -2.78
     horarios
    -2.72
    敍
    -2.70
    POSITIVE LOGITS
    ham
    3.55
     Hundreds
    2.83
     Careful
    2.81
     Simultaneously
    2.78
     
    2.75
    –
    2.75
     Considered
    2.73
    1
    2.69
     ¨
    2.64
     dasarnya
    2.64
    Activations Density 0.010%

    No Known Activations