© 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. 130733
    Prev
    Next
    INDEX
    Explanations

    gases

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

    the word "gases" in technical or scientific contexts.

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

    The neuron consistently activates on occurrences of the word “gases.”

    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
    This
    -2.81
    姈
    -2.75
     For
    -2.63
     flurry
    -2.50
     slew
    -2.33
     fateful
    -2.30
    全然
    -2.28
     Historically
    -2.28
     Which
    -2.28
     Our
    -2.28
    POSITIVE LOGITS
     gases
    2.72
    铼
    2.67
    犼
    2.67
    衚
    2.66
    ſſel
    2.64
     interesado
    2.61
    gucig
    2.39
    ⑊
    2.38
    ᨈ
    2.36
    糨
    2.34
    Activations Density 0.005%

    No Known Activations