© 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. 25025
    Prev
    Next
    INDEX
    Explanations

    words or concepts of requirement

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

    The neuron flags instructional and emphasis cues in technical documentation—i.e. formatting markers (like “>” or “**”) and key action or warning words that denote steps, options, or important notes.

    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
    ampaikan
    -0.77
     tujuan
    -0.76
     Zwecke
    -0.75
    andten
    -0.73
    変わらず
    -0.73
    Ẹ
    -0.71
    арак
    -0.71
     such
    -0.70
    过来了
    -0.70
     피
    -0.69
    POSITIVE LOGITS
     requires
    1.51
    Requires
    1.42
     Requires
    1.36
     require
    1.29
    requires
    1.27
     prerequisite
    1.17
     requiere
    1.14
     nécessite
    1.09
    前提
    1.09
     only
    1.06
    Activations Density 0.059%

    No Known Activations