© 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. 102209
    Prev
    Next
    INDEX
    Explanations

    saline solutions or interstitial fluid

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

    words describing medical or biological tissues, particularly with terms like "interstitial," "saline," and "wholesome."

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

    The neuron is strongly activated by descriptive adjectives characterizing properties (e.g. “wholesome,” “saline,” “interstitial,” “petite,” “stale”).

    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
     pretende
    -2.80
     delightfully
    -2.67
     várias
    -2.67
     The
    -2.64
     praktisch
    -2.56
     momentous
    -2.56
     diversos
    -2.55
     spearheaded
    -2.53
     impone
    -2.53
     häufigsten
    -2.48
    POSITIVE LOGITS
    Even
    2.80
    Surprisingly
    2.50
    you
    2.44
    鋮
    2.44
    鷓
    2.34
    Despite
    2.30
     samme
    2.28
    While
    2.28
     statunitense
    2.28
     untuk
    2.27
    Activations Density 0.004%

    No Known Activations