© 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. 22-GEMMASCOPE-RES-131K
    7. 33087
    Prev
    Next
    INDEX
    Explanations

    proper names and technical terms

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

    This neuron detects numeric tokens in legal documents—especially years, docket numbers, and 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_22/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
    })
    -1.03
     courant
    -1.02
    ској
    -0.97
    quête
    -0.96
     Registro
    -0.96
     superfí
    -0.91
     komfor
    -0.91
     multer
    -0.90
     verre
    -0.90
     DataLoader
    -0.89
    POSITIVE LOGITS
     Oklahoma
    1.17
     Wichita
    1.09
    Oklahoma
    1.05
     stärker
    0.98
     suivie
    0.98
     Otros
    0.96
     svoj
    0.92
     sklo
    0.91
     Tulsa
    0.90
     posled
    0.90
    Activations Density 0.006%

    No Known Activations