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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77063
    Prev
    Next
    INDEX
    Explanations

    No. followed by month or number

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

    The neuron is looking for legal‐case heading markers—especially the “v.” separating parties and the “No.” docket‐number labels.

    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
    gelt
    -0.75
     blues
    -0.74
    urate
    -0.72
     تضيفلها
    -0.71
    urdy
    -0.71
    ็ก
    -0.70
    Renee
    -0.70
     اصلی
    -0.69
    üs
    -0.68
     hayan
    -0.68
    POSITIVE LOGITS
    找个
    0.70
    までも
    0.68
     emiss
    0.67
     ß
    0.66
     tentacles
    0.62
     IA
    0.62
     legged
    0.60
     denied
    0.60
     FOUR
    0.60
    ómo
    0.59
    Activations Density 0.137%

    No Known Activations