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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107512
    Prev
    Next
    INDEX
    Explanations

    canyons, gullies, ridges, and cliffs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on mentions of steep topographical landforms—especially words like “escarpment,” “canyon,” and similar geological slope features.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     hillside
    -0.90
     VALLEY
    -0.85
     valleys
    -0.82
    清单
    -0.81
     Mountains
    -0.81
    ipelago
    -0.79
     valley
    -0.78
     Valley
    -0.78
     mangrove
    -0.77
    consumo
    -0.76
    POSITIVE LOGITS
     rim
    1.28
     Rim
    1.09
     cliff
    1.07
     canyon
    1.03
    壁
    0.95
    Rim
    0.94
     viewpoint
    0.94
     walls
    0.94
     erosion
    0.93
     rims
    0.87
    Activations Density 0.023%

    No Known Activations