© 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. 47089
    Prev
    Next
    INDEX
    Explanations

    measure or status

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

    The neuron activates on words that denote quantitative measurement or indicators (e.g. measure, mean, indicator, score).

    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
    让她
    -0.98
     pourtant
    -0.96
     glisser
    -0.91
    让他们
    -0.90
     constater
    -0.89
     créer
    -0.87
    布置
    -0.87
     regarder
    -0.86
    EDU
    -0.85
    让他
    -0.84
    POSITIVE LOGITS
     overall
    1.57
     how
    1.52
     whether
    1.34
     potential
    1.27
     success
    1.25
     severity
    1.24
     quality
    1.23
     relative
    1.23
     status
    1.21
     likely
    1.21
    Activations Density 0.197%

    No Known Activations