© 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. 10-GEMMASCOPE-RES-131K
    7. 58317
    Prev
    Next
    INDEX
    Explanations

    refactoring and factorization

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

    The neuron detects mentions of “refactor” or “refactoring” (including related tokens like “ref” and “actor”).

    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
    StoryboardSegue
    -2.44
     But
    -1.91
    ского
    -1.82
    e
    -1.81
    鷽
    -1.80
    
    -1.80
    '
    -1.78
    辚
    -1.73
    结局
    -1.69
    ться
    -1.67
    POSITIVE LOGITS
    ↵
    2.52
    —”
    1.92
    </sup>
    1.77
    残酷
    1.73
    </em>
    1.73
     turi
    1.72
    媜
    1.70
     virtù
    1.66
    𓍊
    1.66
     sostanza
    1.65
    Activations Density 0.013%

    No Known Activations