© 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. 128825
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on instructional directive words (e.g. “If,” “uncomment,” “following,” “removed,” “comment”)—i.e. tokens that signal steps or actions in comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code comments and removal

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     saveurs
    -1.11
     těchto
    -1.09
    specifically
    -1.04
     trilha
    -1.02
    ליק
    -1.01
    kinda
    -1.00
     İyi
    -0.99
     člověk
    -0.99
     ovlád
    -0.98
    ushing
    -0.98
    POSITIVE LOGITS
     would
    1.12
     currently
    1.02
     if
    1.02
     add
    1.01
       
    0.97
     or
    0.97
    0.94
     work
    0.93
     presently
    0.93
     now
    0.92
    Activations Density 0.013%

    No Known Activations