© 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. 10-GEMMASCOPE-RES-131K
    7. 102779
    Prev
    Next
    INDEX
    Explanations

    Washington DC

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

    The neuron fires on capitalized named entities—proper names of organizations, places, and similar titles.

    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
    amkeit
    -1.28
    жению
    -1.27
    )
    -1.27
     också
    -1.24
    Галерея
    -1.24
     sabid
    -1.23
     ее
    -1.20
     zů
    -1.19
    ！"
    -1.19
     synchronize
    -1.18
    POSITIVE LOGITS
     Washington
    1.37
    WASHINGTON
    1.34
     WASHINGTON
    1.30
    Conclusión
    1.25
     unofficial
    1.24
     Wasn
    1.21
     washington
    1.20
    maxn
    1.18
     were
    1.17
    Dagger
    1.17
    Activations Density 0.241%

    No Known Activations