© 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. 29913
    Prev
    Next
    INDEX
    Explanations

    Grand slams, triples, career wins

    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
    hoka
    -0.72
     Δη
    -0.70
     getPrice
    -0.69
    bVar
    -0.68
     returnValue
    -0.68
    urture
    -0.66
     used
    -0.65
     풍
    -0.65
    といっても
    -0.64
     Chinatown
    -0.63
    POSITIVE LOGITS
     Grand
    2.09
     Triple
    1.87
    Grand
    1.81
     grand
    1.77
    grand
    1.64
     GRAND
    1.63
    Triple
    1.62
     triple
    1.52
    GRAND
    1.44
     quadruple
    1.37
    Activations Density 0.032%

    No Known Activations