© 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. 22-GEMMASCOPE-RES-131K
    7. 24990
    Prev
    Next
    INDEX
    Explanations

    programming contexts

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

    The neuron fires on schedule‐and‐deadline language—phrases laying out timing or milestone plans (e.g. “mid-June,” “first draft report by early/mid July”).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    उ
    -0.94
    HAND
    -0.93
     سيارة
    -0.92
     Allez
    -0.91
     cầu
    -0.89
    mRNA
    -0.86
     nombreuses
    -0.86
    RICK
    -0.85
    确实是
    -0.85
    dito
    -0.84
    POSITIVE LOGITS
    +}\
    0.95
     augusztus
    0.94
     június
    0.91
    msleep
    0.91
    grade
    0.90
     július
    0.88
     fVar
    0.87
     április
    0.87
     to
    0.85
     only
    0.85
    Activations Density 0.326%

    No Known Activations