© 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. 34-GEMMASCOPE-RES-131K
    4. 84808
    Prev
    Next
    INDEX
    Explanations

    hyphenated surnames

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

    The neuron activates on personal names, especially capitalized first and last names (often hyphenated), identifying mentions of people.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     variante
    -0.97
    orama
    -0.97
    -"
    -0.96
    iko
    -0.89
    нитель
    -0.88
     Nota
    -0.87
    hauses
    -0.87
    тору
    -0.87
     Fé
    -0.86
    唐揚げ
    -0.86
    POSITIVE LOGITS
    ようですが
    1.05
     acestea
    1.04
    silla
    1.00
     combatir
    1.00
    -
    0.96
     venezol
    0.96
    ことです
    0.95
     причине
    0.94
     recogida
    0.94
    感じが
    0.94
    Activations Density 0.053%

    No Known Activations