© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59814
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms

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

    The neuron fires on named entities and other multi‐letter capitalized terms (e.g. proper names, journal titles, technical library or module names).

    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
    ፒ
    -2.81
    ዡ
    -2.81
    ྃ
    -2.80
    鬭
    -2.56
    鼇
    -2.55
     vader
    -2.53
    Ꮔ
    -2.52
    鈇
    -2.45
    一个是
    -2.44
     decorados
    -2.42
    POSITIVE LOGITS
    та
    3.19
    𖤍
    2.78
    </h3>
    2.73
                
    2.56
    enablog
    2.50
    )
    2.42
    峮
    2.38
              
    2.38
    ه
    2.38
        
    2.34
    Activations Density 0.009%

    No Known Activations