© 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. 56749
    Prev
    Next
    INDEX
    Explanations

    lesson or conclusion

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

    The neuron is specialized in spotting numeric tokens (digits and numbers) within 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
    kaido
    -0.86
     drodze
    -0.86
     okresie
    -0.85
     zuerst
    -0.85
    strophy
    -0.84
    BorderLayout
    -0.83
    xec
    -0.83
    ronpa
    -0.82
    exus
    -0.81
    inematic
    -0.80
    POSITIVE LOGITS
     moral
    3.50
    Bottom
    3.19
     bottom
    3.16
    Moral
    3.16
     Moral
    3.03
    moral
    2.94
     conclusion
    2.86
     Bottom
    2.83
     lesson
    2.81
     point
    2.67
    Activations Density 0.034%

    No Known Activations