© 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. 129036
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily detecting numeric data tokens (numbers and measurements) in the text.

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

    highest, lowest, fastest, slowest

    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
     already
    -1.06
    riculares
    -1.00
     later
    -0.98
     into
    -0.94
     späteren
    -0.93
    teryx
    -0.93
    ección
    -0.92
     AtomicInteger
    -0.90
    hilation
    -0.87
    Claudio
    -0.82
    POSITIVE LOGITS
     fewest
    1.22
    least
    1.02
     lowest
    1.02
    Least
    0.98
     least
    0.96
    lowest
    0.92
     warum
    0.88
     slowest
    0.88
    疊
    0.86
    给大家
    0.84
    Activations Density 0.031%

    No Known Activations