© 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. 69999
    Prev
    Next
    INDEX
    Explanations

    licenses

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

    The neuron strongly activates on words tied to the commercial cannabis industry—especially terms around dispensaries, sales, licenses, and adult‐use marijuana.

    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
     smoking
    -0.98
     Sì
    -0.87
     smoked
    -0.85
     Smoking
    -0.84
    pania
    -0.77
     Oltre
    -0.77
     ganas
    -0.75
    Smoking
    -0.75
     Dred
    -0.73
    客室
    -0.73
    POSITIVE LOGITS
     license
    1.14
     licensee
    1.13
    license
    1.12
     licenses
    1.11
     licensing
    1.05
     licensed
    1.02
     licence
    1.02
     licensees
    0.94
     retail
    0.93
     Licence
    0.91
    Activations Density 0.026%

    No Known Activations