© 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. 73746
    Prev
    Next
    INDEX
    Explanations

    rules, system, consistency

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

    The neuron activates on numerical tokens and measurements (numbers, decimals, and other quantity expressions).

    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
    Usually
    -1.31
     обычно
    -1.26
    Still
    -1.22
    Typically
    -1.18
     usually
    -1.16
     vesel
    -1.15
    Faça
    -1.13
     suele
    -1.10
    いかがでしたか
    -1.09
     деца
    -1.04
    POSITIVE LOGITS
     better
    1.68
     proper
    1.47
     improved
    1.43
     properly
    1.30
     uniform
    1.24
     endlich
    1.24
     наконец
    1.16
     uniformity
    1.15
    better
    1.13
     clearer
    1.13
    Activations Density 0.029%

    No Known Activations