© 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. 25046
    Prev
    Next
    INDEX
    Explanations

    work and other environments

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

    The neuron activates selectively on the word “environment.”

    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
    頗
    -1.60
     dovr
    -1.45
     egentlig
    -1.38
     rozmiar
    -1.34
     dipinto
    -1.28
    脸上
    -1.25
     dirit
    -1.21
    纔
    -1.21
     soumettre
    -1.20
    춤
    -1.20
    POSITIVE LOGITS
     environment
    2.14
     where
    1.83
     Those
    1.52
     ambiente
    1.52
     conditions
    1.48
     
    1.46
     donde
    1.42
     ortam
    1.40
     of
    1.38
     criado
    1.38
    Activations Density 0.037%

    No Known Activations