© 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. 84211
    Prev
    Next
    INDEX
    Explanations

    specific words followed by certain names/terms

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

    The neuron primarily activates on numeric tokens—measurements, years, figure numbers, and other standalone 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
    Przypisy
    -0.79
     sand
    -0.78
    영화
    -0.75
     Kull
    -0.73
     becomes
    -0.73
    Conserv
    -0.72
    Bore
    -0.71
     Dase
    -0.71
    edm
    -0.71
     信
    -0.70
    POSITIVE LOGITS
     Strecke
    0.91
     fels
    0.79
     normative
    0.78
     Jogo
    0.77
    analytical
    0.75
    🌋
    0.75
    amples
    0.73
     química
    0.72
     mantle
    0.72
     AFRICA
    0.71
    Activations Density 0.007%

    No Known Activations