© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42976
    Prev
    Next
    INDEX
    Explanations

    parsing programming code

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

    This neuron fires on occurrences of the literal string “parse” (including in identifiers or comments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ?"
    -2.39
     và
    -2.31
    泐
    -2.22
    й
    -2.22
    Ꭸ
    -2.17
     destined
    -2.16
    髕
    -2.14
     vedere
    -2.11
    を中心
    -2.11
    倘
    -2.08
    POSITIVE LOGITS
    đầm
    2.39
    {
    2.34
     lesquelles
    2.31
    ⃢
    2.28
     aina
    2.20
    1
    2.16
    
    2.16
     samma
    2.14
     exquisite
    2.14
    because
    2.14
    Activations Density 0.006%

    No Known Activations