© 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. 22-GEMMASCOPE-RES-131K
    7. 32880
    Prev
    Next
    INDEX
    Explanations

    labels and identifiers

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

    The neuron is detecting primary‐key or identifier annotations (e.g. @Id, @PrimaryKey) in code.

    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
     to
    -1.37
    ⿵
    -1.25
    acknow
    -1.24
     entire
    -1.23
     proporciona
    -1.22
    向了
    -1.20
    setArguments
    -1.17
    蛱
    -1.17
     know
    -1.16
     kwiet
    -1.16
    POSITIVE LOGITS
     beszél
    1.08
    e
    1.00
    There
    0.98
    option
    0.95
             
    0.94
    ,
    0.93
        
    0.90
    maso
    0.90
         
    0.88
    options
    0.88
    Activations Density 0.001%

    No Known Activations