© 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. 6829
    Prev
    Next
    INDEX
    Explanations

    icon and legend descriptors

    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
     nové
    -1.49
     οι
    -1.41
     new
    -1.40
     nový
    -1.39
     They
    -1.33
     моя
    -1.31
    ?"
    -1.28
     ними
    -1.25
     betrifft
    -1.24
     betrug
    -1.23
    POSITIVE LOGITS
    Unfortunately
    1.66
     sagen
    1.44
     Jenderal
    1.40
     manuale
    1.37
     icona
    1.36
     Ambos
    1.35
     државе
    1.31
     القيام
    1.27
     字母
    1.27
     priva
    1.27
    Activations Density 0.053%

    No Known Activations