© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4363
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly selective for occurrences of the word “science.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     developers
    0.87
    ש
    0.86
     TOE
    0.82
     perfusion
    0.80
    apped
    0.79
     absorbed
    0.79
     innovators
    0.78
     qPCR
    0.78
     DNA
    0.76
     monol
    0.76
    POSITIVE LOGITS
    timestamps
    0.83
     térmica
    0.68
    periods
    0.67
     príncipe
    0.67
    
    0.65
    ži
    0.64
    
    0.63
     razón
    0.63
     temporadas
    0.63
     সদ
    0.62
    Activations Density 0.000%

    No Known Activations