© 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. 106131
    Prev
    Next
    INDEX
    Explanations

    fast, accurate, efficient, reliable descriptors

    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
    Speed
    -1.77
     speed
    -1.73
    speed
    -1.66
    速度
    -1.63
    SPEED
    -1.55
     Speed
    -1.40
     скорость
    -1.32
    的速度
    -1.32
    スピード
    -1.32
     velocity
    -1.29
    POSITIVE LOGITS
     furious
    1.17
     painless
    0.94
    反應
    0.87
     accuracy
    0.81
     accurate
    0.81
     Furious
    0.77
    反应
    0.76
     accurately
    0.74
    sieur
    0.73
    estres
    0.72
    Activations Density 0.056%

    No Known Activations