© 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. 11321
    Prev
    Next
    INDEX
    Explanations

    feature

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

    The neuron activates on words that call out key aspects or traits—terms like “feature,” “features,” or “characteristics” that introduce important properties.

    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
    鬈
    -1.70
     acepción
    -1.70
    inl
    -1.67
     estadía
    -1.66
     颜
    -1.61
    らせる
    -1.59
    💜
    -1.57
     faſt
    -1.56
    nachweise
    -1.55
     exhibición
    -1.55
    POSITIVE LOGITS
    除此之外
    1.77
    3
    1.70
     THIS
    1.64
    荅
    1.63
      
    1.63
        
    1.62
     What
    1.60
    除此
    1.60
            
    1.59
    独自の
    1.59
    Activations Density 0.033%

    No Known Activations