© 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. 79315
    Prev
    Next
    INDEX
    Explanations

    code and technical scripts

    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
    Karena
    -0.88
    easier
    -0.86
     Installing
    -0.86
    uric
    -0.86
    givers
    -0.85
    ଂ
    -0.85
     resim
    -0.84
     baj
    -0.84
     effet
    -0.83
     chasse
    -0.83
    POSITIVE LOGITS
     it
    0.97
     seleccione
    0.91
    orros
    0.82
    IonicModule
    0.81
     آید
    0.80
     Hütte
    0.80
     Werken
    0.79
     fijar
    0.79
    importe
    0.76
    Adverse
    0.76
    Activations Density 0.007%

    No Known Activations