© 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. 22568
    Prev
    Next
    INDEX
    Explanations

    loving and caring expressions

    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
    s
    -1.76
     EVERYTHING
    -1.73
     EVERYONE
    -1.70
     Если
    -1.65
    -1.63
    Rptr
    -1.54
    zerland
    -1.53
    име
    -1.53
     Año
    -1.52
    】
    -1.52
    POSITIVE LOGITS
     and
    2.53
     see
    1.70
     viejas
    1.55
    νης
    1.48
     ولكن
    1.44
    when
    1.42
     beschrieben
    1.41
     prisão
    1.40
     tornando
    1.39
    烩
    1.38
    Activations Density 0.005%

    No Known Activations