© 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. 22-GEMMASCOPE-RES-131K
    7. 36007
    Prev
    Next
    INDEX
    Explanations

    math equations with variables

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

    This neuron fires on tokens that represent numerical values (digits or numeric measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     component
    -0.87
    wanda
    -0.80
    ANCH
    -0.79
     ukry
    -0.79
     pe
    -0.76
     behind
    -0.75
    anch
    -0.75
     arbeitet
    -0.74
    ごろ
    -0.74
     minimum
    -0.73
    POSITIVE LOGITS
    Зачем
    0.94
     робити
    0.93
    同士
    0.93
     salat
    0.92
    Ար
    0.91
    лимпи
    0.89
     levis
    0.88
    }>
    0.87
     kano
    0.86
    Again
    0.85
    Activations Density 0.035%

    No Known Activations