© 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. 22-GEMMASCOPE-RES-131K
    7. 95375
    Prev
    Next
    INDEX
    Explanations

    following Category or code snippets

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

    The neuron fires on HTML tag delimiters, especially the “<script” tag opener.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     صغيرة
    -1.01
     ähnlichen
    -0.99
     skoro
    -0.98
    einem
    -0.98
     Similarly
    -0.95
    limard
    -0.94
    Similarly
    -0.91
    both
    -0.91
     During
    -0.89
    кухня
    -0.89
    POSITIVE LOGITS
     domic
    1.02
     Paramètres
    0.96
    ētu
    0.96
     hôtes
    0.94
     all
    0.93
    ⿴
    0.90
     vado
    0.89
     mises
    0.88
     précédents
    0.88
     etc
    0.87
    Activations Density 0.008%

    No Known Activations