© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83166
    Prev
    Next
    INDEX
    Explanations

    New York Times bestseller list

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

    The neuron detects mentions of “New York Times” best‐seller status (e.g. “ten-time New York Times bestselling author,” “New York Times Best Selling”).

    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
    しても
    -0.82
     ValidationError
    -0.81
     too
    -0.77
     denied
    -0.76
     deadly
    -0.75
     paliwa
    -0.74
     besucht
    -0.74
     vergeben
    -0.74
     ErrInvalid
    -0.74
     damage
    -0.74
    POSITIVE LOGITS
     listes
    1.00
     liste
    0.98
     bekle
    0.96
     risiko
    0.94
     salg
    0.92
     list
    0.88
     Fortune
    0.87
     anse
    0.86
     bestseller
    0.85
     LIST
    0.85
    Activations Density 0.015%

    No Known Activations