© 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. 85171
    Prev
    Next
    INDEX
    Explanations

    tracking trends and activities

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

    The neuron fires on occurrences of the root “track” (e.g. track, tracking, tracked).

    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
    ↵↵
    -3.16
    "
    -2.22
    ."
    -1.98
    на
    -1.90
    kirakan
    -1.70
            
    -1.66
     one
    -1.66
    .'
    -1.63
     chapter
    -1.63
    >
    -1.63
    POSITIVE LOGITS
     thier
    2.27
     všetkých
    2.25
    ೢ
    2.17
    ientos
    2.00
    li
    1.98
    ーーー
    1.94
    
    1.94
     každého
    1.92
    妞
    1.92
     endure
    1.90
    Activations Density 0.016%

    No Known Activations