© 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. 60334
    Prev
    Next
    INDEX
    Explanations

    legal case and patent numbers

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

    The neuron activates on isolated digits within formal identifiers (like catalog numbers, case or patent citation numbers).

    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
     like
    -1.90
     something
    -1.74
     so
    -1.64
     M
    -1.63
     S
    -1.61
     the
    -1.59
     D
    -1.57
     probably
    -1.56
     it
    -1.56
     some
    -1.55
    POSITIVE LOGITS
     magasiner
    1.95
     tirs
    1.94
     plafon
    1.90
     patienter
    1.88
     maksi
    1.87
     thoſe
    1.84
    𓁹
    1.81
     célè
    1.79
     fidé
    1.78
     menyen
    1.77
    Activations Density 0.258%

    No Known Activations