© 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. 34-GEMMASCOPE-RES-131K
    7. 115892
    Prev
    Next
    INDEX
    Explanations

    code and its context

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

    This neuron detects references to “code” identifiers or numeric codes (e.g. tokens like “Code,” “Código,” “codigo” and the associated numbers).

    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
    abyrinth
    -0.80
    heet
    -0.71
    Ponto
    -0.70
    ո
    -0.70
    urable
    -0.68
    ophen
    -0.68
    Injection
    -0.66
    gründ
    -0.66
     capacidad
    -0.66
    Inclusive
    -0.65
    POSITIVE LOGITS
     barras
    1.15
     Barra
    0.99
     доступа
    0.91
     barre
    0.90
    barre
    0.90
     source
    0.89
     postal
    0.86
    fecture
    0.85
     verification
    0.83
     confirmación
    0.81
    Activations Density 0.042%

    No Known Activations