© 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. 3459
    Prev
    Next
    INDEX
    Explanations

    legal, technical, and specific topics

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

    The neuron activates on numeric tokens (years, version numbers, quantities, etc.).

    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
     Gemü
    -0.88
    onen
    -0.88
    مود
    -0.84
     Ärz
    -0.75
     vostri
    -0.75
     Layla
    -0.75
     yıll
    -0.75
    før
    -0.74
    matician
    -0.73
    qui
    -0.72
    POSITIVE LOGITS
    Uses
    0.84
     общения
    0.84
    ：
    0.80
    InstanceOf
    0.77
     leurs
    0.77
    Pennsylvania
    0.74
     pochod
    0.74
    veloppe
    0.73
    喙
    0.72
     nied
    0.72
    Activations Density 0.010%

    No Known Activations