© 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. 80612
    Prev
    Next
    INDEX
    Explanations

    word endings for names

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

    The neuron detects fragments of capitalized proper names or named entities (person, place, or title).

    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
    几个月
    -2.16
    
    -2.14
     sogen
    -2.13
    的态度
    -2.13
     Artículos
    -2.05
    的情绪
    -2.05
     وفي
    -2.05
    见状
    -2.02
     zusätz
    -1.98
     unangemess
    -1.98
    POSITIVE LOGITS
    </th>
    2.64
    </h1>
    2.56
    ↵↵
    2.50
    捭
    2.42
    </u>
    2.34
    }$
    2.28
     Перейти
    2.23
    piecze
    2.20
    '
    2.19
    </i>
    2.14
    Activations Density 0.353%

    No Known Activations