© 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. 34-GEMMASCOPE-RES-131K
    7. 103698
    Prev
    Next
    INDEX
    Explanations

    must retain copyright

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

    This neuron detects license‐style requirement clauses, especially imperatives like “must retain” in software license texts.

    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
    emias
    -0.74
     putter
    -0.67
    GeneratedMessage
    -0.67
    ̓
    -0.66
     校
    -0.66
    CIAS
    -0.66
     CATEGORIES
    -0.66
    chand
    -0.66
     Clears
    -0.65
     Reino
    -0.63
    POSITIVE LOGITS
    ²,
    0.71
     SPC
    0.65
     Parte
    0.65
     Review
    0.65
     SUPPORT
    0.63
     SUB
    0.62
    cube
    0.61
    资
    0.61
    hlí
    0.60
     Chrys
    0.60
    Activations Density 0.093%

    No Known Activations