© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31705
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    This neuron detects the all-caps party or judge names and other uppercase identifiers in legal case citations.

    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
     but
    -1.20
    ┌
    -0.88
     beaute
    -0.88
    บริการ
    -0.85
     intención
    -0.83
    警察
    -0.82
     bookseller
    -0.81
     formular
    -0.81
    kových
    -0.79
     Morph
    -0.79
    POSITIVE LOGITS
     ép
    0.93
     የ
    0.91
    潆
    0.90
    了啊
    0.87
     juger
    0.87
    trout
    0.87
     esfuerzan
    0.85
     обеспечи
    0.85
    itom
    0.85
     sich
    0.84
    Activations Density 0.011%

    No Known Activations