© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129106
    Prev
    Next
    INDEX
    Explanations

    html head

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

    The neuron fires on HTML markup indicators—especially the literal “html” token in doctype declarations, meta tags, and opening/closing tags.

    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
            
    -1.54
     obtend
    -1.53
    鰱
    -1.38
     manifestazione
    -1.36
     spécialisé
    -1.33
     セール
    -1.30
         
    -1.29
    inosa
    -1.27
     Eröffnung
    -1.26
     obtuvo
    -1.25
    POSITIVE LOGITS
     on
    1.80
    婳
    1.71
    蜮
    1.70
     anderen
    1.68
    
    1.67
     unut
    1.62
     kemer
    1.60
    かというと
    1.55
     eser
    1.51
    håll
    1.50
    Activations Density 0.005%

    No Known Activations