© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32904
    Prev
    Next
    INDEX
    Explanations

    net amount, price, velocity, result

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

    The neuron activates on numerical expressions—digits, counts, percentages, and other number tokens.

    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
     الفن
    -0.96
     colorear
    -0.83
     solucionar
    -0.82
    llon
    -0.82
     funcionários
    -0.81
    春季
    -0.79
     alimentación
    -0.78
     verbind
    -0.77
     jazdy
    -0.77
     Galer
    -0.76
    POSITIVE LOGITS
     net
    1.79
     overall
    1.36
    net
    1.34
     Net
    1.12
    Net
    1.11
     NET
    1.08
     nets
    1.06
     still
    1.05
    NET
    1.03
    balance
    1.02
    Activations Density 0.032%

    No Known Activations