© 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. 79378
    Prev
    Next
    INDEX
    Explanations

    python imports and code structure

    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
    vedì
    -0.76
    bash
    -0.75
    reli
    -0.75
    fontsize
    -0.72
     your
    -0.69
    dma
    -0.69
     any
    -0.69
     düğün
    -0.68
    eran
    -0.68
    我了
    -0.67
    POSITIVE LOGITS
    diagnostic
    0.87
     diagnostics
    0.84
     Diagnostic
    0.82
    diagnostics
    0.81
     diagnostic
    0.78
    omaterials
    0.76
    quiry
    0.75
     diagnosis
    0.73
    naire
    0.71
     priorities
    0.71
    Activations Density 0.004%

    No Known Activations