© 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. 79419
    Prev
    Next
    INDEX
    Explanations

    pointing, stressing, praising

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

    The neuron strongly responds to numeric tokens and formatted numbers (e.g. dates, timestamps, and digit sequences).

    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
     even
    -0.90
    増
    -0.84
     навіть
    -0.84
    帮助
    -0.80
     but
    -0.79
    Phil
    -0.78
    自己的
    -0.77
     Phil
    -0.77
     I
    -0.77
    Granted
    -0.77
    POSITIVE LOGITS
     pointed
    1.05
     pointing
    1.02
     stressed
    0.97
     stresses
    0.97
     praising
    0.91
    EMPLOY
    0.91
    CAPIT
    0.91
    IFICA
    0.89
    ߌ
    0.88
     stressing
    0.88
    Activations Density 0.008%

    No Known Activations