© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33603
    Prev
    Next
    INDEX
    Explanations

    California Air Control District

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

    The neuron fires on references to specific statutes, amendments, or other legal citations—especially year numbers and formal act titles.

    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
     sak
    -0.70
     ден
    -0.69
    Barg
    -0.68
    ނ
    -0.65
     shaking
    -0.65
     triangulation
    -0.65
    出会い
    -0.65
    roughts
    -0.64
    ghost
    -0.63
    oliber
    -0.63
    POSITIVE LOGITS
     air
    0.98
    เครื่อง
    0.96
    Air
    0.92
    AQ
    0.90
     AQ
    0.88
     Stationary
    0.88
     stationary
    0.87
     Corse
    0.85
    air
    0.84
    District
    0.84
    Activations Density 0.009%

    No Known Activations