© 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. 72743
    Prev
    Next
    INDEX
    Explanations

    programming, technical, and personal terms

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

    The neuron fires on infrequent, specialized tokens—e.g. technical identifiers, jargon, or proper‐name–style words.

    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
     curtailed
    -2.69
    ⦊
    -2.56
     ſont
    -2.52
    retario
    -2.48
     nourished
    -2.44
    
    -2.44
     refuted
    -2.42
     kunjung
    -2.41
    ية
    -2.39
    魠
    -2.39
    POSITIVE LOGITS
    ’
    4.25
            
    2.88
        
    2.61
    an
    2.58
      
    2.52
    s
    2.50
                 
    2.42
    );
    2.41
    если
    2.39
    你喜欢
    2.39
    Activations Density 0.008%

    No Known Activations