© 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. 47759
    Prev
    Next
    INDEX
    Explanations

    Tuning Metal-Organic Frameworks

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

    real estate listings and property descriptions with location details.

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

    The neuron activates on numerical mentions—digits, measurements, and quantitative figures.

    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
    ждении
    -0.91
     silvestre
    -0.90
     eloku
    -0.85
    جام
    -0.82
    onde
    -0.81
     deserto
    -0.81
    逛
    -0.78
     零
    -0.78
     Arxivat
    -0.77
    ágico
    -0.77
    POSITIVE LOGITS
     €
    1.07
     property
    1.02
     PROPERTY
    1.00
     golf
    0.98
     Property
    0.98
     Golf
    0.94
     EU
    0.94
     UK
    0.94
    property
    0.94
     foreigners
    0.93
    Activations Density 0.017%

    No Known Activations