© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33523
    Prev
    Next
    INDEX
    Explanations

    groundwater, springs, and ground truth

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

    references to groundwater or underground water resources in environmental and geological 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
    ienes
    -0.79
    lumb
    -0.79
    Når
    -0.77
     groundwater
    -0.76
    Pooling
    -0.74
    Lambda
    -0.73
     geração
    -0.73
     filmp
    -0.73
     ground
    -0.72
    GROUND
    -0.71
    POSITIVE LOGITS
     Mathews
    0.77
     conditions
    0.75
    blockList
    0.74
     Lev
    0.72
    viste
    0.69
     Zhi
    0.69
    lja
    0.68
    NUMERIC
    0.67
    سرائ
    0.67
    getTarget
    0.66
    Activations Density 0.018%

    No Known Activations