© 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. 10-GEMMASCOPE-RES-131K
    7. 60602
    Prev
    Next
    INDEX
    Explanations

    District of Columbia Circuit

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

    This neuron responds to formal names of governmental or legal entities (e.g. legislation titles, courts, or official territorial 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_10/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
     diversos
    -1.38
     constater
    -1.20
    leſs
    -1.20
     costruire
    -1.20
     diversas
    -1.18
    ませて
    -1.18
     supplé
    -1.12
     sería
    -1.12
     Ê
    -1.11
    来到了
    -1.11
    POSITIVE LOGITS
     while
    1.57
    snprintf
    1.37
    Even
    1.28
     even
    1.20
     with
    1.16
     légale
    1.11
     despite
    1.11
    pNext
    1.09
    While
    1.08
     जबकि
    1.08
    Activations Density 0.059%

    No Known Activations