© 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. 22-GEMMASCOPE-RES-131K
    7. 130016
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric tokens (numbers, including multi‐digit and decimal figures).

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

    patent numbers and citations

    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
     has
    -1.36
     have
    -1.09
     '${
    -1.06
     does
    -1.04
     will
    -1.02
     provides
    -1.01
     seemed
    -1.00
     their
    -0.98
     gives
    -0.97
     before
    -0.96
    POSITIVE LOGITS
    might
    1.17
    especially
    1.15
    imo
    1.13
    particularly
    1.13
    different
    1.09
     magnific
    1.08
    both
    1.08
     DIFFERENT
    1.05
    Important
    1.05
    ment
    1.05
    Activations Density 0.002%

    No Known Activations