© 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. 79310
    Prev
    Next
    INDEX
    Explanations

    policy, practice, and legislation

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

    The neuron flags formal academic/policy jargon—words like “policy,” “theory,” “implementation,” “evaluation,” “research,” “legal,” “programs,” etc.

    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
    𝐙
    -0.93
    пія
    -0.92
    THEW
    -0.90
    reurs
    -0.86
     viņ
    -0.86
    elancer
    -0.85
    بسم
    -0.85
    SEPTEMBER
    -0.85
    jaro
    -0.84
     etc
    -0.84
    POSITIVE LOGITS
     strategy
    1.89
     practices
    1.87
     procedures
    1.84
     procedure
    1.78
     practice
    1.73
     policy
    1.62
     programs
    1.58
     legislation
    1.55
     operations
    1.53
     policies
    1.50
    Activations Density 0.054%

    No Known Activations