© 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. 34-GEMMASCOPE-RES-131K
    7. 56859
    Prev
    Next
    INDEX
    Explanations

    colors describing items

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ͅ
    -1.09
     professionali
    -1.04
    знес
    -0.92
     tassels
    -0.88
     цвете
    -0.88
    ajā
    -0.82
    ']).
    -0.81
    ことなく
    -0.80
    raux
    -0.80
     〜
    -0.79
    POSITIVE LOGITS
     white
    3.94
     black
    3.86
     yellow
    3.22
     blue
    3.08
     brown
    3.03
     red
    3.00
     gray
    2.95
     green
    2.88
     orange
    2.86
     pink
    2.73
    Activations Density 0.111%

    No Known Activations