© 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. 83815
    Prev
    Next
    INDEX
    Explanations

    used to introduce descriptions

    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
     for
    -2.30
     through
    -2.27
     using
    -2.20
     as
    -1.97
     first
    -1.82
     since
    -1.80
     just
    -1.75
     that
    -1.72
     one
    -1.70
     could
    -1.68
    POSITIVE LOGITS
     rafraî
    1.63
     véhic
    1.52
     énorm
    1.51
     tromper
    1.48
     refroid
    1.48
    ſo
    1.46
     manquer
    1.45
     déliv
    1.45
    These
    1.44
     ___________
    1.44
    Activations Density 0.395%

    No Known Activations