© 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. 48597
    Prev
    Next
    INDEX
    Explanations

    license, licensing, licensed

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

    This neuron detects mentions of licensing or permission terms (e.g., license, licensed, licensing, sublicense).

    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
    weist
    -0.77
    Ikus
    -0.76
     persec
    -0.74
    øren
    -0.72
    ẤT
    -0.71
    чої
    -0.70
    riment
    -0.70
    xAxis
    -0.70
    츄
    -0.69
    ליון
    -0.68
    POSITIVE LOGITS
     licensing
    5.47
     license
    5.13
     licence
    4.75
     licensed
    4.72
     licenses
    4.56
     Licensing
    4.38
    license
    4.25
     licen
    4.19
     License
    4.19
    License
    4.09
    Activations Density 0.080%

    No Known Activations