© 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. 56828
    Prev
    Next
    INDEX
    Explanations

    motorcycle names and models

    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
    onik
    -0.75
    нутрен
    -0.72
    コンビ
    -0.71
    Justification
    -0.69
    barten
    -0.69
    告诉我
    -0.69
    楽しく
    -0.67
     inserir
    -0.66
    даго
    -0.65
    слі
    -0.65
    POSITIVE LOGITS
     naked
    1.00
     Naked
    0.97
     CBR
    0.95
     Indus
    0.94
     Japanese
    0.93
    Japanese
    0.92
    Tracer
    0.84
    TEC
    0.84
     Duke
    0.82
     FZ
    0.82
    Activations Density 0.029%

    No Known Activations