© 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. 11789
    Prev
    Next
    INDEX
    Explanations

    license, lease, or franchise permissions

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

    The neuron is highly sensitive to terms and phrases around official licenses and permissions (e.g., “license,” “licenses,” “granted,” “issued”).

    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
     impul
    -0.81
    օ
    -0.78
    FINISHED
    -0.77
    Kirch
    -0.77
     Sya
    -0.77
     ASPECTS
    -0.75
    jumu
    -0.75
     kwa
    -0.75
    Apt
    -0.75
    etna
    -0.74
    POSITIVE LOGITS
     granted
    1.32
     holders
    1.19
     holder
    1.14
     license
    1.13
     issued
    1.11
     licence
    1.11
     otorg
    1.07
     lease
    1.04
     renewal
    1.02
     License
    1.02
    Activations Density 0.007%

    No Known Activations