© 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. 79316
    Prev
    Next
    INDEX
    Explanations

    describing conditions or states

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

    The neuron selectively activates on numeric values (counts, measurements, years, or other quantitative data).

    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
    lof
    -0.96
    nare
    -0.91
    caping
    -0.91
    carus
    -0.90
    ølge
    -0.90
     polluted
    -0.87
    进攻
    -0.86
    vermectin
    -0.85
    それが
    -0.84
    addCell
    -0.84
    POSITIVE LOGITS
     caused
    1.86
     treated
    1.17
    caused
    1.14
     detected
    1.14
     Caused
    1.12
     preventable
    1.09
     associated
    1.04
     prevented
    1.01
     diagnosed
    1.00
     not
    0.99
    Activations Density 0.158%

    No Known Activations