© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31066
    Prev
    Next
    INDEX
    Explanations

    currency amounts and symbols

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

    The neuron fires on numeric tokens denoting monetary amounts (prices with currency symbols).

    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
    cheri
    -0.82
     excesso
    -0.79
    vtk
    -0.79
    万円
    -0.76
    ゲ
    -0.73
    rawtypes
    -0.73
    ੧
    -0.73
    érèse
    -0.73
     sha
    -0.72
    chomp
    -0.71
    POSITIVE LOGITS
     sisält
    0.82
     Contributions
    0.82
    Зе
    0.80
     délicieux
    0.78
    udios
    0.77
     entrance
    0.72
    ᴜ
    0.71
     donation
    0.70
     Grilled
    0.70
    municip
    0.70
    Activations Density 0.009%

    No Known Activations