© 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. 3691
    Prev
    Next
    INDEX
    Explanations

    abbreviations and titles

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

    The neuron activates on numeric tokens (digits and numbers) 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
     Bibel
    -0.84
    HttpGet
    -0.79
    ajari
    -0.78
    AVI
    -0.76
    람
    -0.74
    ituksen
    -0.74
     galaxia
    -0.74
     Naciones
    -0.73
    brat
    -0.72
     während
    -0.71
    POSITIVE LOGITS
     amélior
    0.90
     disadvantages
    0.85
     disad
    0.77
    われている
    0.75
     uph
    0.75
    Disadvantages
    0.74
     baisse
    0.74
     commemorate
    0.72
     bought
    0.72
    း
    0.72
    Activations Density 0.004%

    No Known Activations