© 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. 10-GEMMASCOPE-RES-131K
    4. 101571
    Prev
    Next
    INDEX
    Explanations

    corporate and MERCHANTABILITY

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

    the word "MERCHANTABILITY" in software license text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on tokens containing the substring “corpor,” e.g. in words like “corporatist,” “corporately,” or “merchantability.”

    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
    2
    -3.42
    y
    -3.41
     Which
    -3.36
     \
    -3.25
    3
    -3.22
    廡
    -3.16
    5
    -2.98
     \"
    -2.92
    7
    -2.92
    8
    -2.91
    POSITIVE LOGITS
    岿
    2.92
     августа
    2.86
    gesterone
    2.83
    ם
    2.73
     ouverture
    2.70
    鼷
    2.64
    咔嚓
    2.61
    铼
    2.58
    秾
    2.56
     skóra
    2.55
    Activations Density 0.008%

    No Known Activations