© 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. 34-GEMMASCOPE-RES-131K
    7. 4096
    Prev
    Next
    INDEX
    Explanations

    view, art, door, after, teen, further

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

    The neuron fires strongly on words that occur immediately next to explicit numeric references (i.e. tokens directly adjacent to numbers).

    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
    ized
    -0.88
     Winning
    -0.70
    sin
    -0.70
     туры
    -0.69
    しまう
    -0.69
    ﾚ
    -0.69
    itarian
    -0.67
    kingen
    -0.67
    ності
    -0.66
     ország
    -0.66
    POSITIVE LOGITS
    ¬
    1.05
    ­
    0.94
    work
    0.94
    міністра
    0.85
    cote
    0.84
    place
    0.82
    wok
    0.82
    𝙟
    0.81
     besoins
    0.81
    Weiß
    0.81
    Activations Density 0.106%

    No Known Activations