© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54316
    Prev
    Next
    INDEX
    Explanations

    boolean comparisons

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

    This neuron activates on CamelCase or PascalCase identifiers (multi-word or mixed-case names) 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
     Quelle
    -0.98
    ndan
    -0.94
    cetos
    -0.92
    皝
    -0.92
     conflicto
    -0.92
     reçoit
    -0.92
     servir
    -0.91
    のまま
    -0.91
     imprime
    -0.90
     esos
    -0.90
    POSITIVE LOGITS
     Wszyst
    0.94
     medica
    0.93
    venty
    0.91
     and
    0.88
     emoticon
    0.85
     discri
    0.84
     isEqualToString
    0.84
    ous
    0.83
    HasColumnName
    0.83
     모든
    0.82
    Activations Density 0.000%

    No Known Activations