© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12145
    Prev
    Next
    INDEX
    Explanations

    salt and salinity

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

    mentions of salt, saline compounds, and halophilic (salt-loving) organisms in scientific or culinary contexts.

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

    The neuron highlights mentions of salt or salinity (e.g. “salt,” “saline,” “halophilic,” “sodium transporter”) in a scientific context.

    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
     Ethanol
    -0.98
     methanol
    -0.86
     ALCOHOL
    -0.82
    unesse
    -0.80
     هوا
    -0.79
     ethanol
    -0.78
     Alcohol
    -0.77
     styrene
    -0.77
     Methanol
    -0.77
     bourbon
    -0.75
    POSITIVE LOGITS
     salt
    4.25
    salt
    3.52
    Salt
    3.38
     Salt
    3.38
     salty
    3.34
     salts
    3.30
     NaCl
    2.91
    SALT
    2.89
     SALT
    2.75
    NaCl
    2.72
    Activations Density 0.066%

    No Known Activations