© 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. 78073
    Prev
    Next
    INDEX
    Explanations

    water salinity and types

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

    text related to water salinity, particularly mentions of brackish, freshwater, or saltwater environments.

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

    The neuron flags numerical measurement expressions—numbers together with scientific units (e.g. temperature, pH, percentages).

    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
     tube
    -0.75
    habhar
    -0.73
    PLATE
    -0.73
    tiz
    -0.71
     detachment
    -0.70
     식
    -0.67
    phite
    -0.67
     Oxford
    -0.67
    HTTP
    -0.66
    CodeAttribute
    -0.66
    POSITIVE LOGITS
     salinity
    2.48
     salt
    1.95
     Salinity
    1.89
     salty
    1.88
     saltwater
    1.88
    salt
    1.66
     freshwater
    1.65
     seawater
    1.63
    fresh
    1.58
     Salt
    1.57
    Activations Density 0.028%

    No Known Activations