© 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. 2801
    Prev
    Next
    INDEX
    Explanations

    growing and rotten food

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

    words related to items, resources, or materials in games or farming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     gatos
    -0.83
    modal
    -0.78
    μβρίου
    -0.78
     Lowe
    -0.75
    Emil
    -0.75
     opgenomen
    -0.73
    Первый
    -0.72
     निर्माण
    -0.72
    ンダント
    -0.71
    开发
    -0.71
    POSITIVE LOGITS
     harves
    1.02
     grow
    1.00
     crop
    0.94
     yield
    0.94
     growth
    0.94
     Growth
    0.93
     crops
    0.89
     plant
    0.88
    互动
    0.87
     Grow
    0.84
    Activations Density 0.010%

    No Known Activations