© 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. 10-GEMMASCOPE-RES-131K
    7. 40316
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    The neuron is detecting numeric literals and arithmetic expressions (numbers, including signed and decimal values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     There
    -1.95
     first
    -1.89
    C
    -1.79
    M
    -1.79
     there
    -1.76
    There
    -1.69
    デメリット
    -1.69
    P
    -1.69
    1
    -1.63
     reducing
    -1.63
    POSITIVE LOGITS
     zoude
    1.97
     insanely
    1.88
     Профиль
    1.84
    
    1.84
     okno
    1.83
    
    1.81
    đu
    1.80
    »?
    1.80
    verwijs
    1.78
     semelh
    1.77
    Activations Density 0.093%

    No Known Activations