© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117303
    Prev
    Next
    INDEX
    Explanations

    topography, terrain, and landscape

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Dichlorobenzene
    -0.86
    "}";
    -0.85
    tront
    -0.83
     Staining
    -0.80
     GBIF
    -0.79
     sạn
    -0.78
     Yank
    -0.78
    lenül
    -0.77
    葯
    -0.77
     Україні
    -0.76
    POSITIVE LOGITS
     topography
    4.16
     terrain
    4.13
     geography
    2.95
    terrain
    2.88
     topo
    2.84
     topology
    2.67
     Terrain
    2.55
    地形
    2.52
     Topography
    2.45
    topo
    2.44
    Activations Density 0.060%

    No Known Activations