© 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. 56739
    Prev
    Next
    INDEX
    Explanations

    public code entities

    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
     beagle
    -0.90
    épendance
    -0.79
     mule
    -0.75
     jacob
    -0.74
    mule
    -0.73
     flax
    -0.71
    ndale
    -0.68
     SDR
    -0.67
    Falcon
    -0.65
    yaç
    -0.65
    POSITIVE LOGITS
    dungen
    0.84
    ccion
    0.82
    isbn
    0.77
    的食物
    0.77
    咲
    0.75
    {!
    0.75
     lids
    0.75
     Inglaterra
    0.74
    typed
    0.73
    西藏
    0.73
    Activations Density 0.059%

    No Known Activations