© 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. 56919
    Prev
    Next
    INDEX
    Explanations

    out of

    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
    چھ
    -0.84
     linh
    -0.81
     pretty
    -0.80
     вниз
    -0.79
     less
    -0.78
     cualquiera
    -0.77
     двох
    -0.77
     Б
    -0.76
     نهاية
    -0.76
     two
    -0.75
    POSITIVE LOGITS
     of
    3.92
     out
    1.16
    ของ
    1.13
     của
    1.09
    Out
    0.97
    隕
    0.91
     mété
    0.90
    standigheden
    0.88
     sés
    0.87
     xícara
    0.85
    Activations Density 0.008%

    No Known Activations