© 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. 99961
    Prev
    Next
    INDEX
    Explanations

    Kum, Lauderdale, Guadalupe, Glendale

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

    The neuron fires on capitalized proper names—especially uncommon personal or place names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    proper nouns—especially names beginning with the syllable “Kum,” and more broadly names with distinctive u-vowel clusters.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the name "Kumashiro" or words beginning with "Kum" (particularly proper nouns and names).

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    u
    -2.72
    ᵴ
    -2.70
    琑
    -2.63
    ꜆
    -2.58
    
    -2.53
    "}}>
    -2.42
    est
    -2.42
     выборе
    -2.36
    緇
    -2.34
    y
    -2.31
    POSITIVE LOGITS
    趼
    2.45
     médicale
    2.33
     Мы
    2.28
    Reprodução
    2.25
    "
    2.23
     uren
    2.17
    蕺
    2.17
    🢒
    2.14
     内衣
    2.11
    儈
    2.11
    Activations Density 0.001%

    No Known Activations