© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84842
    Prev
    Next
    INDEX
    Explanations

    immigration and commissions

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

    The neuron is strongly activated by all-caps headings, titles, and docket-style tokens (e.g., court names, parties, dates, and other formal header elements) in legal documents.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     charismatic
    -0.84
    从小
    -0.83
    ètement
    -0.81
    timedia
    -0.81
    cmds
    -0.79
     medios
    -0.78
    commands
    -0.78
    communications
    -0.76
     Command
    -0.74
     京
    -0.74
    POSITIVE LOGITS
     immigration
    1.13
     Immigration
    1.00
    Restriction
    0.94
     Restriction
    0.94
     restriction
    0.93
     restrictive
    0.91
     quotas
    0.84
     Ellis
    0.81
     restri
    0.80
     quota
    0.79
    Activations Density 0.016%

    No Known Activations