© 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. 22-GEMMASCOPE-RES-131K
    7. 129288
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to mentions of numeric quantities or counting terms (digits, numbers, averages, counts, steps, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    minimum cost or steps

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     capabilities
    -0.91
     Marrakech
    -0.88
    Стро
    -0.88
     funt
    -0.88
    olska
    -0.87
     作業
    -0.86
     vole
    -0.85
    zę
    -0.84
     图标
    -0.83
     restricting
    -0.82
    POSITIVE LOGITS
     cost
    1.30
     wasted
    1.27
     costs
    1.24
     spent
    1.15
     distance
    1.08
     затра
    0.98
    cost
    0.95
     coût
    0.94
    argmin
    0.93
     expenses
    0.93
    Activations Density 0.011%

    No Known Activations