© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128006
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily activates on numeric tokens (numbers and numeric citations/statistical values) in the text.

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

    citations and references

    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
     noticeable
    -1.07
     each
    -1.06
    */].
    -1.02
    ὸς
    -1.02
    ).__
    -0.98
    []{"
    -0.97
     nearing
    -0.95
     over
    -0.92
     every
    -0.91
     concerning
    -0.90
    POSITIVE LOGITS
    which
    1.04
     WHICH
    0.99
     нашего
    0.95
     but
    0.95
    ショット
    0.94
    nie
    0.94
    seer
    0.94
     déterminer
    0.93
     cintur
    0.93
     conſ
    0.93
    Activations Density 0.058%

    No Known Activations