© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21423
    Prev
    Next
    INDEX
    Explanations

    water quality parameters

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

    scientific terms related to chemical compounds and measurements in environmental science.

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

    The main thing this neuron does is find mentions of specific quantitative environmental or chemical water‐quality parameters (e.g., concentrations or removal metrics like SS, COD, pH, salinity, dissolved oxygen).

    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
     with
    -1.44
    ;
    
    -1.41
     музея
    -1.35
    ↵↵
    -1.33
    :+:
    -1.27
    lossal
    -1.27
    #%%
    
    -1.27
    tifs
    -1.23
     организма
    -1.23
     Europe
    -1.22
    POSITIVE LOGITS
    изображение
    1.37
     generalmente
    1.32
    oció
    1.30
    พาะ
    1.29
     persoonlijke
    1.27
     normalmente
    1.23
     широко
    1.23
    section
    1.23
    outons
    1.21
     encontramos
    1.20
    Activations Density 0.049%

    No Known Activations