© 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. 34-GEMMASCOPE-RES-131K
    7. 107018
    Prev
    Next
    INDEX
    Explanations

    code identifiers and auto-generation

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

    This neuron detects primary‐key or ID annotations (e.g. @Id, @GeneratedValue, @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_34/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
     Restoration
    -0.92
     restored
    -0.91
     restoration
    -0.89
     Restore
    -0.88
    ങ്ങള
    -0.84
    ncy
    -0.83
    bedrijf
    -0.83
     pulseras
    -0.83
    hộp
    -0.82
     invitaciones
    -0.82
    POSITIVE LOGITS
    GeneratedValue
    1.35
    generate
    1.11
    generator
    1.00
    auto
    0.94
    generated
    0.90
     generators
    0.89
     generator
    0.87
     generate
    0.84
     generated
    0.84
     generating
    0.81
    Activations Density 0.003%

    No Known Activations