© 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. 56773
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     ē
    -0.90
    炬
    -0.90
    viewDidLoad
    -0.88
    strich
    -0.88
    kı
    -0.84
    Visualization
    -0.81
    commons
    -0.80
    farbe
    -0.78
    rally
    -0.78
    batsman
    -0.77
    POSITIVE LOGITS
     bề
    0.81
    常に
    0.74
    //(
    0.73
    uhan
    0.72
    Millan
    0.70
    datalist
    0.70
    rentice
    0.69
     versuchen
    0.69
     발생
    0.68
    Buildable
    0.68
    Activations Density 0.133%

    No Known Activations