© 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. 79465
    Prev
    Next
    INDEX
    Explanations

    altitude and elevation

    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
     渡
    -0.81
     nhàng
    -0.80
    OMEN
    -0.79
     cytos
    -0.78
    weightedMode
    -0.78
    ång
    -0.77
    nesc
    -0.76
    ząd
    -0.76
    سكرية
    -0.76
    ótico
    -0.75
    POSITIVE LOGITS
     altitude
    4.53
     elevation
    3.64
    altitude
    3.39
     altitudes
    3.23
    Altitude
    3.03
     Altitude
    2.81
    elevation
    2.81
     elevations
    2.69
     Elevation
    2.67
    Elevation
    2.59
    Activations Density 0.048%

    No Known Activations