© 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. 63714
    Prev
    Next
    INDEX
    Explanations

    renal transplantation

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

    content related to geographic information systems and satellite imagery, particularly Google Earth Engine.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on code‐like tokens—especially programming keywords, API identifiers, and function calls (notably Google Earth Engine terms).

    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
     Hound
    -0.89
    rials
    -0.86
    aris
    -0.79
    ARIS
    -0.77
    tabular
    -0.76
     Pion
    -0.74
     Refining
    -0.74
    ranean
    -0.74
    🤢
    -0.73
    estros
    -0.73
    POSITIVE LOGITS
     Landsat
    1.04
     cloud
    0.83
    orith
    0.79
     Transplant
    0.75
     band
    0.74
    GEE
    0.71
     vrst
    0.70
    carb
    0.69
    Clouds
    0.69
     ee
    0.68
    Activations Density 0.015%

    No Known Activations