© 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. 30913
    Prev
    Next
    INDEX
    Explanations

    commercial production, airline, vehicles, artist, print, license

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

    The neuron activates on occurrences of the word “commercial.”

    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
     伸
    -0.91
    」(
    -0.89
    ıdır
    -0.87
    اء
    -0.86
    ltä
    -0.85
     scrittore
    -0.84
    Jako
    -0.82
    łoży
    -0.81
    Cru
    -0.81
    Ekster
    -0.79
    POSITIVE LOGITS
    ization
    1.82
    commercial
    1.70
     commercial
    1.59
    ised
    1.50
     Commercial
    1.41
     COMMERCIAL
    1.40
    Commercial
    1.39
    ized
    1.34
    izable
    1.24
    isation
    1.23
    Activations Density 0.018%

    No Known Activations