© 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. 34-GEMMASCOPE-RES-131K
    7. 106223
    Prev
    Next
    INDEX
    Explanations

    hasOwnProperty check

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

    The neuron fires most strongly on numeric literals (i.e. digit‐only tokens) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     essayé
    -0.82
     embreagem
    -0.81
    啬
    -0.76
     refusé
    -0.76
    owano
    -0.75
    等的
    -0.74
     espagne
    -0.73
     kış
    -0.73
    creamy
    -0.71
    𝖕
    -0.71
    POSITIVE LOGITS
    hasOwnProperty
    1.09
    property
    0.90
     property
    0.81
     deepening
    0.79
     OWN
    0.79
    Granted
    0.79
     owne
    0.78
    Underline
    0.74
    bezirk
    0.74
    prototype
    0.73
    Activations Density 0.007%

    No Known Activations