© 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. 128863
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on quoted identifier strings (e.g. names, labels, or keys) in code or markup.

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

    code delimiters and structure

    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
    などを
    -1.20
     Ausdrücke
    -1.09
    很快就
    -1.08
    たたみ
    -1.04
     những
    -1.03
     außerdem
    -1.01
     $
    -1.00
     exoner
    -1.00
     Teilen
    -0.99
    を
    -0.99
    POSITIVE LOGITS
    siamo
    1.26
    1.16
     ***!
    1.11
     núcleos
    1.11
    irical
    1.10
    1.09
    pergillus
    1.07
    Tú
    1.07
    ̴
    1.07
     costuras
    1.06
    Activations Density 0.016%

    No Known Activations