© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11636
    Prev
    Next
    INDEX
    Explanations

    international proper nouns and place names

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

    The neuron detects proper nouns or named entities, especially capitalized names of people, places, organizations, or 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
     that
    -1.85
     їх
    -1.65
     wherein
    -1.63
     Their
    -1.62
     and
    -1.59
     Dzięki
    -1.56
    ,\\
    -1.56
    },
    -1.48
     Jeśli
    -1.48
    tický
    -1.45
    POSITIVE LOGITS
    着一
    1.67
    -
    1.52
     soldat
    1.51
     ‘
    1.48
     to
    1.48
    着一个
    1.46
     a
    1.41
     organisme
    1.32
     monstre
    1.32
    Follow
    1.31
    Activations Density 0.133%

    No Known Activations