© 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. 22-GEMMASCOPE-RES-131K
    7. 84132
    Prev
    Next
    INDEX
    Explanations

    Q: and blog

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

    The neuron strongly activates on the conjunction “and.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.18
     both
    -1.06
     those
    -0.99
     PyTuple
    -0.98
    izado
    -0.95
     this
    -0.94
     összefoglaló
    -0.94
     реши
    -0.93
     anyone
    -0.85
     cilindro
    -0.85
    POSITIVE LOGITS
     ссылке
    1.07
    仍然
    1.07
     OGSÅ
    1.05
     recibirá
    1.00
     giudizio
    0.98
     élar
    0.94
    jsonp
    0.94
    izu
    0.92
     partecipare
    0.91
    zensionen
    0.90
    Activations Density 0.000%

    No Known Activations