© 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. 10-GEMMASCOPE-RES-131K
    7. 38353
    Prev
    Next
    INDEX
    Explanations

    free movement, market, speech, trade

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

    This neuron primarily detects occurrences of the word “free.”

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    𓍊
    -1.71
     patience
    -1.48
     Coloque
    -1.43
     petite
    -1.41
    やお
    -1.41
     Forgot
    -1.40
     сход
    -1.39
     trips
    -1.37
    挖掘
    -1.37
     gracefully
    -1.36
    POSITIVE LOGITS
     начали
    1.86
     был
    1.73
    when
    1.64
    􀂃
    1.61
     When
    1.53
    9
    1.47
    was
    1.46
     Bahkan
    1.45
     Keuangan
    1.44
     був
    1.42
    Activations Density 0.026%

    No Known Activations