© 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. 98849
    Prev
    Next
    INDEX
    Explanations

    look to or turn to

    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
    脔
    -1.67
     alimen
    -1.60
    uminense
    -1.59
    ichtete
    -1.56
    祧
    -1.55
    vade
    -1.52
    {
    -1.52
    aksana
    -1.52
    putar
    -1.50
    𖧵
    -1.50
    POSITIVE LOGITS
     to
    3.64
     for
    2.13
    an
    1.55
     from
    1.54
     aprobó
    1.45
     Lidé
    1.43
     help
    1.43
    lepší
    1.40
     /
    1.39
     gradual
    1.31
    Activations Density 0.015%

    No Known Activations