© 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. 106140
    Prev
    Next
    INDEX
    Explanations

    crack down

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

    The neuron detects strong enforcement or crackdown language (e.g. terms implying forceful restriction or suppression).

    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
    gean
    -0.81
    make
    -0.76
     Period
    -0.73
    taco
    -0.73
     Village
    -0.73
    Village
    -0.71
    gb
    -0.71
     VILLAGE
    -0.71
    -_
    -0.71
    phins
    -0.70
    POSITIVE LOGITS
    від
    0.75
    Venta
    0.71
    Rotated
    0.69
    testData
    0.68
    Luxem
    0.66
     populist
    0.65
    wsgi
    0.65
    prä
    0.65
     Himalaya
    0.65
     oku
    0.63
    Activations Density 0.086%

    No Known Activations