© 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. 62613
    Prev
    Next
    INDEX
    Explanations

    auto-generated method stub

    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
     roda
    -0.96
     dizi
    -0.90
    ्ट
    -0.86
     paiement
    -0.84
    ąg
    -0.83
     字符
    -0.82
     ritmo
    -0.82
     dinam
    -0.81
     plát
    -0.80
     frigor
    -0.80
    POSITIVE LOGITS
     by
    1.19
     generated
    1.05
    auto
    0.99
     method
    0.97
    Generated
    0.97
     Method
    0.96
     stub
    0.94
    Method
    0.93
     methods
    0.92
     anbieten
    0.92
    Activations Density 0.002%

    No Known Activations