© 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. 34-GEMMASCOPE-RES-131K
    4. 98017
    Prev
    Next
    INDEX
    Explanations

    licence.txt

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

    This neuron detects boilerplate license‐grant language, specifically the conditional phrasing (e.g. “use,” “provided,” “conditions are met”) in software licensing clauses.

    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
    統領
    -0.73
     Tower
    -0.73
     cooks
    -0.73
     weddings
    -0.73
    債
    -0.71
     looms
    -0.70
    isShowing
    -0.70
     courtroom
    -0.68
    アント
    -0.67
    rist
    -0.67
    POSITIVE LOGITS
     Jeans
    0.75
    Jeans
    0.71
    incenti
    0.71
    jeans
    0.69
    故事
    0.68
    beard
    0.67
     Pender
    0.66
    beh
    0.63
     stood
    0.62
    astronomie
    0.62
    Activations Density 0.054%

    No Known Activations