© 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. 10-GEMMASCOPE-RES-131K
    7. 14543
    Prev
    Next
    INDEX
    Explanations

    with followed by article or description

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

    The neuron specializes in spotting numeric values and quantities (integers or decimals) within 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_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
     you
    -1.79
    C
    -1.74
     these
    -1.73
     our
    -1.68
            
    -1.62
     every
    -1.58
     obecnie
    -1.55
    -1.55
     people
    -1.49
    for
    -1.46
    POSITIVE LOGITS
     memeriksa
    1.84
    ’,
    1.80
    getInfo
    1.55
    Fourni
    1.50
    
    1.48
    depuis
    1.47
    ܆
    1.47
    \%,
    1.45
     raça
    1.44
    鼷
    1.43
    Activations Density 0.032%

    No Known Activations