© 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. 81623
    Prev
    Next
    INDEX
    Explanations

    legal matters and clinics

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

    The neuron fires on multi‐word proper names of legal organizations or official bodies.

    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
     bribes
    -0.81
    éroport
    -0.80
    angulo
    -0.77
    Купить
    -0.77
    Jeb
    -0.74
    wieder
    -0.73
     HIT
    -0.71
     Dex
    -0.71
    itter
    -0.71
     файла
    -0.71
    POSITIVE LOGITS
     clinic
    1.64
     Clinic
    1.38
    clinic
    1.27
     clinics
    1.23
     lawyers
    1.20
     representation
    1.18
     legal
    1.13
    Clinic
    1.13
     attorneys
    1.13
     Legal
    1.13
    Activations Density 0.043%

    No Known Activations