© 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. 29891
    Prev
    Next
    INDEX
    Explanations

    musical theatre

    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
     Calvo
    -0.79
    reen
    -0.77
    ylem
    -0.77
    Itoa
    -0.75
     tepung
    -0.71
     inflammatory
    -0.71
    ilit
    -0.71
     рит
    -0.71
     gustaría
    -0.71
    τητα
    -0.71
    POSITIVE LOGITS
     Phantom
    1.43
    Phantom
    1.30
     phantom
    1.09
     Christine
    1.09
    Christine
    1.00
    Erik
    0.98
     Erik
    0.94
     chandelier
    0.88
     masked
    0.88
     gothic
    0.87
    Activations Density 0.010%

    No Known Activations