© 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. 113303
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

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

    The neuron strongly activates on numeric tokens—i.e., it spots numbers (including integers and decimals).

    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
    ↵↵
    -3.36
    6
    -2.50
    7
    -2.19
    5
    -2.14
    8
    -2.09
    3
    -1.97
    1
    -1.91
    4
    -1.84
    0
    -1.76
    <i>
    -1.72
    POSITIVE LOGITS
     like
    1.90
    ⼈
    1.78
     protège
    1.74
     desaparecido
    1.73
    
    1.66
     entendido
    1.66
     experimentado
    1.66
     marcado
    1.66
     anunciado
    1.61
    磲
    1.60
    Activations Density 0.077%

    No Known Activations