© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13984
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

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

    The neuron activates whenever it sees numeric digits (numbers) in the text.

    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
    뾰
    -0.92
     complementar
    -0.90
     paillettes
    -0.89
     both
    -0.85
    providedIn
    -0.84
    дования
    -0.83
     trigo
    -0.83
    setItems
    -0.82
     alun
    -0.82
    metres
    -0.81
    POSITIVE LOGITS
     cuối
    0.97
     fifth
    0.88
     четыре
    0.87
    4
    0.86
     kolejny
    0.86
     tambin
    0.85
     очеред
    0.84
     canh
    0.84
    은
    0.83
     ninth
    0.82
    Activations Density 0.048%

    No Known Activations