© 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. 22-GEMMASCOPE-RES-131K
    7. 15706
    Prev
    Next
    INDEX
    Explanations

    followed by specific words

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

    The neuron specifically fires on C/C++ preprocessor include statements—detecting the “include” keyword and its following path tokens.

    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
     by
    -1.26
    未来的
    -1.09
     for
    -1.09
     беже
    -1.05
     throughout
    -1.00
    就行了
    -0.98
     it
    -0.96
    しさ
    -0.96
     to
    -0.94
     its
    -0.94
    POSITIVE LOGITS
    ји
    0.99
    異なる
    0.99
    
    0.97
     måste
    0.96
     arī
    0.96
    党
    0.96
     encontraba
    0.95
     seules
    0.94
    不时
    0.94
     reguli
    0.94
    Activations Density 0.000%

    No Known Activations