© 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. 128199
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric tokens (integers or decimals) in the text.

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

    coordinates and numbers

    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
     will
    -1.45
    
    -1.12
    Zubereitung
    -1.00
    と言われる
    -0.96
     desmotiv
    -0.94
    ontroller
    -0.92
    ઃ
    -0.92
     words
    -0.92
     that
    -0.91
    pantal
    -0.91
    POSITIVE LOGITS
    क्र
    1.07
    ."\
    1.06
    아
    1.05
     صغيرة
    1.03
    Sens
    1.01
    Difference
    1.01
     ग्राहकों
    0.98
    ផ
    0.98
    rafat
    0.98
    uoš
    0.98
    Activations Density 0.002%

    No Known Activations