© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32684
    Prev
    Next
    INDEX
    Explanations

    email, file, javascript links

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

    The neuron fires on the literal token “javascript” (as used in script tags, language attributes, or the “javascript:” URL scheme).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     которы
    -1.30
    跸
    -1.30
     nieuwe
    -1.27
     ľudí
    -1.27
    オシャレ
    -1.22
     vaše
    -1.21
     této
    -1.20
     distinctive
    -1.20
     obyvateľov
    -1.20
    が行
    -1.17
    POSITIVE LOGITS
    –
    1.10
    1.08
    there
    1.07
    。　
    1.06
    ://
    1.05
    Surprisingly
    1.05
           
    1.04
     vitrine
    1.03
    Despite
    1.01
                  
    1.00
    Activations Density 0.001%

    No Known Activations