© 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. 34-GEMMASCOPE-RES-131K
    7. 78864
    Prev
    Next
    INDEX
    Explanations

    applicable law

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

    The neuron specifically detects the occurrence of the word “applicable,” as used repeatedly in license‐boilerplate phrases (e.g. “applicable law”).

    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
    inyl
    -0.71
     预
    -0.65
    탕
    -0.64
    KommentareTeilen
    -0.62
    Breaker
    -0.61
    Pou
    -0.60
     stripe
    -0.60
     correctly
    -0.59
    ュー
    -0.59
    ściej
    -0.58
    POSITIVE LOGITS
    モー
    0.80
    каче
    0.72
     henkilö
    0.72
     temperatur
    0.70
    ↹
    0.69
     Railroad
    0.68
     Flaming
    0.68
    arra
    0.67
    IVEN
    0.67
     industriel
    0.67
    Activations Density 0.066%

    No Known Activations