© 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. 10-GEMMASCOPE-RES-131K
    7. 129409
    Prev
    Next
    INDEX
    Explanations

    commas

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric expressions (e.g. measurements, version numbers, dates, sizes with units).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     hogyan
    -2.09
    ⎘
    -2.05
    
    -2.03
     delectable
    -1.97
    瓛
    -1.96
    퐹
    -1.94
     modificaciones
    -1.88
     ſy
    -1.88
    튿
    -1.86
     ſou
    -1.84
    POSITIVE LOGITS
     can
    3.06
     has
    2.72
    $
    2.41
     will
    2.41
     because
    2.39
     then
    2.23
     (
    2.08
    They
    2.03
    This
    2.02
     includes
    2.02
    Activations Density 0.020%

    No Known Activations