© 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. 6812
    Prev
    Next
    INDEX
    Explanations

    ability to do

    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
     作り方
    -2.02
     étan
    -2.02
     două
    -1.92
    桖
    -1.89
    瞜
    -1.89
     moldura
    -1.86
    owym
    -1.84
    　　（
    -1.84
     motocicleta
    -1.83
    豋
    -1.83
    POSITIVE LOGITS
     to
    4.34
     of
    2.98
     on
    2.94
     from
    2.67
     for
    2.59
     in
    2.56
     by
    2.41
    4
    2.05
     as
    1.95
     --
    1.91
    Activations Density 0.004%

    No Known Activations