© 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. 58106
    Prev
    Next
    INDEX
    Explanations

    read more

    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
     if
    -1.95
     you
    -1.86
     However
    -1.63
     Another
    -1.61
     Because
    -1.58
     If
    -1.52
     Some
    -1.52
    Another
    -1.50
     {
    -1.49
     neuen
    -1.48
    POSITIVE LOGITS
    蛱
    1.51
    plenty
    1.50
     omt
    1.48
    brilliant
    1.48
     gruppe
    1.44
     zul
    1.43
    ."</
    1.41
    HAHA
    1.40
    GillaGilla
    1.39
     incrí
    1.38
    Activations Density 0.006%

    No Known Activations