© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116424
    Prev
    Next
    INDEX
    Explanations

    business chains and franchises

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

    The neuron activates on mentions of restaurants or restaurant‐chain names (i.e., references to dining establishments).

    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
     Section
    -0.89
     newly
    -0.88
     techniques
    -0.87
     section
    -0.86
     designated
    -0.85
     predstav
    -0.83
     profondità
    -0.80
    ▃
    -0.79
    ěry
    -0.79
     wüns
    -0.78
    POSITIVE LOGITS
     chain
    1.91
    chain
    1.49
     chains
    1.45
     franch
    1.45
     cadena
    1.32
    Locations
    1.29
    Chain
    1.29
     magasins
    1.18
     CHAIN
    1.17
     chaîne
    1.16
    Activations Density 0.064%

    No Known Activations