© 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. 47208
    Prev
    Next
    INDEX
    Explanations

    software support

    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
    確認
    -0.75
     сер
    -0.70
    чностью
    -0.70
     tuyến
    -0.69
     Stefano
    -0.69
     ciclismo
    -0.69
     Curtain
    -0.67
    ⌊
    -0.66
     військо
    -0.66
     crescent
    -0.65
    POSITIVE LOGITS
     media
    1.17
     tracks
    1.16
     constraints
    0.98
    gum
    0.96
     menghadapi
    0.94
     Media
    0.93
    media
    0.93
     mídia
    0.91
    constraints
    0.89
     agarose
    0.88
    Activations Density 0.014%

    No Known Activations