© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94265
    Prev
    Next
    INDEX
    Explanations

    soil aggregation and structure

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

    words related to soil properties and characteristics.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
     '-')
    -0.77
    ség
    -0.77
    ⋉
    -0.75
    diya
    -0.75
    tagName
    -0.75
    luci
    -0.74
    叠
    -0.73
    uced
    -0.73
    juris
    -0.71
     abon
    -0.69
    POSITIVE LOGITS
     aggregates
    1.04
     aggregate
    1.03
     physical
    1.00
    aggreg
    0.97
     structure
    0.97
    aggregation
    0.94
    aggregate
    0.93
     aggregation
    0.93
     structural
    0.89
    Aggregation
    0.85
    Activations Density 0.009%

    No Known Activations