© 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. 128670
    Prev
    Next
    INDEX
    Explanations

    the neuron detects and highlights numeric expressions (digits, quantities, and numbers).

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

    scientific and mathematical terms

    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
     considera
    -0.94
     этих
    -0.82
    で見る
    -0.79
    aned
    -0.79
    appear
    -0.77
    mon
    -0.77
    нены
    -0.77
     HAPPENED
    -0.76
    hn
    -0.75
    N
    -0.75
    POSITIVE LOGITS
     Reihen
    0.91
    vriende
    0.90
     menangis
    0.90
     Headache
    0.84
     Gerichte
    0.82
    illées
    0.82
    mıştır
    0.82
    Eerste
    0.80
    骞
    0.78
     médicaux
    0.77
    Activations Density 0.108%

    No Known Activations