© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42668
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -1.41
     in
    -1.20
     just
    -1.08
    らかに
    -1.03
     all
    -0.99
     found
    -0.96
     both
    -0.95
     and
    -0.94
    .
    -0.94
     those
    -0.92
    POSITIVE LOGITS
    ㉔
    1.20
     secrétaire
    1.16
    ㉓
    1.15
    astră
    1.01
     unfor
    1.00
    але
    0.99
    drei
    0.99
     但
    0.98
     taşlı
    0.96
     centrale
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.