© 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. 10-GEMMASCOPE-RES-131K
    7. 90636
    Prev
    Next
    INDEX
    Explanations

    natural water sources

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

    water features like springs, fountains, wells, and pools in natural or constructed settings.

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

    The main thing this neuron does is detect mentions of natural water sources (e.g., springs, wells, and related 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_10/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
     a
    -1.83
     ۷
    -1.71
     the
    -1.61
     Grüße
    -1.61
     pf
    -1.60
    </
    -1.55
     hohen
    -1.49
     somewhat
    -1.48
     ۶
    -1.45
     способы
    -1.45
    POSITIVE LOGITS
    Ruju
    1.66
    ượu
    1.62
    行政区划
    1.50
    🐣
    1.44
     perplexing
    1.42
     abiertas
    1.42
    푣
    1.42
     from
    1.41
    ériale
    1.41
    Both
    1.40
    Activations Density 0.031%

    No Known Activations