© 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. 34-GEMMASCOPE-RES-131K
    7. 63943
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron strongly activates on isolated numeric tokens (digits or numbers).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ámicas
    -0.93
     червня
    -0.80
    iency
    -0.79
     namens
    -0.78
    整備
    -0.78
    PREFERRED
    -0.77
     Poni
    -0.77
     Perspek
    -0.77
     consectetur
    -0.77
    iD
    -0.77
    POSITIVE LOGITS
     Any
    0.80
    的消息
    0.77
     Florida
    0.70
     Erkenntnis
    0.68
     ordinarily
    0.68
    必然
    0.68
     erfordert
    0.68
    ubin
    0.68
     sichtbar
    0.67
    琦
    0.66
    Activations Density 0.000%

    No Known Activations