© 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. 85175
    Prev
    Next
    INDEX
    Explanations

    localhost URLs

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

    The neuron never activates on any of the tokens shown—it doesn’t detect any recurring pattern in these examples.

    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
     his
    -1.68
     enfati
    -1.55
     in
    -1.55
    felpa
    -1.54
     autre
    -1.53
     ktore
    -1.53
     humild
    -1.51
     Sábado
    -1.51
     desmotiv
    -1.49
     marcó
    -1.48
    POSITIVE LOGITS
     miliardi
    1.69
    1.66
            
    1.63
        
    1.54
    if
    1.48
                
    1.46
    &
    1.46
    	
    1.46
    \">
    1.45
    om
    1.41
    Activations Density 0.011%

    No Known Activations