© 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. 10-GEMMASCOPE-RES-131K
    7. 129130
    Prev
    Next
    INDEX
    Explanations

    popular [noun]

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

    The neuron fires on occurrences of the word “popular.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    僦
    -2.95
    ⻬
    -2.78
     superb
    -2.67
     unbelievably
    -2.67
     they
    -2.66
     planific
    -2.66
    蹰
    -2.64
     marvelous
    -2.64
     monstrous
    -2.61
     неболь
    -2.58
    POSITIVE LOGITS
    d
    3.52
    a
    3.03
    禤
    3.00
    晅
    2.91
    an
    2.86
     tetapi
    2.81
    ஂ
    2.78
    n
    2.78
    鋮
    2.78
    
    2.77
    Activations Density 0.016%

    No Known Activations