© 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. 12042
    Prev
    Next
    INDEX
    Explanations

    arrests, applications, and law

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

    The neuron strongly activates on tokens in legal‐news contexts, especially around remands and custody (e.g. “sent,” “to,” “till,” “remanded,” “custody”).

    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
    EFIAPI
    -0.80
     heart
    -0.79
     koszt
    -0.72
    cama
    -0.68
    pende
    -0.68
     Lazy
    -0.68
     UNS
    -0.67
     prioritized
    -0.66
     celery
    -0.66
     pią
    -0.66
    POSITIVE LOGITS
     summoned
    0.92
     summoning
    0.90
    Police
    0.90
     anticip
    0.90
    sessions
    0.87
     bail
    0.84
    кг
    0.81
    召唤
    0.80
     Datos
    0.77
     Police
    0.77
    Activations Density 0.009%

    No Known Activations