© 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. 106295
    Prev
    Next
    INDEX
    Explanations

    clock time, positions, six

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

    The neuron is triggered by explicit clock‐time expressions (e.g. “at the six o’clock hour,” “at 12 o’clock”).

    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
     선택
    -0.81
    occhio
    -0.77
    fono
    -0.75
     nhôm
    -0.74
     século
    -0.73
    烫
    -0.73
     淡
    -0.73
     aula
    -0.73
     сможет
    -0.73
     răm
    -0.72
    POSITIVE LOGITS
     noon
    1.36
     position
    1.14
     positions
    1.11
     Noon
    1.11
    Noon
    1.08
    positions
    1.05
     положении
    1.00
     Six
    0.97
     six
    0.96
    noon
    0.95
    Activations Density 0.010%

    No Known Activations