© 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. 59225
    Prev
    Next
    INDEX
    Explanations

    place names and identifiers

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

    The neuron fires on numeric tokens (i.e. any standalone numbers or digit sequences) in the text.

    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
     technology
    -0.83
     säga
    -0.78
     Technology
    -0.78
     strategy
    -0.77
     infantry
    -0.77
     strategies
    -0.74
     vecka
    -0.73
    兵
    -0.73
    nefs
    -0.71
     Mechan
    -0.71
    POSITIVE LOGITS
    Stiftung
    0.80
    CountDown
    0.80
    enschaften
    0.77
    pted
    0.74
     adep
    0.72
    ritis
    0.71
    userid
    0.70
    Ϯ
    0.70
    Women
    0.70
     MAL
    0.69
    Activations Density 0.009%

    No Known Activations