© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7378
    Prev
    Next
    INDEX
    Explanations

    licenses and agreements

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

    The neuron detects occurrences of the word “Agreement” (and its plural “agreements”), typically capitalized in legal or licensing text.

    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
     the
    -2.66
    埽
    -2.47
     impromptu
    -2.39
     exceedingly
    -2.36
     decidedly
    -2.31
    
    -2.30
    數
    -2.28
    眼前的
    -2.22
    ໊
    -2.22
     stalwart
    -2.20
    POSITIVE LOGITS
    ).
    2.92
    鎗
    2.30
    箩
    2.28
    しますが
    2.08
    because
    2.08
    稗
    2.05
    呖
    2.02
    縷
    1.98
    してみると
    1.98
    There
    1.98
    Activations Density 0.009%

    No Known Activations