© 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. 102887
    Prev
    Next
    INDEX
    Explanations

    as a result or consequence

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

    This neuron detects the discourse connective phrase “As a result” introducing a consequence.

    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
     perle
    -0.88
     turist
    -0.85
     boh
    -0.84
     mè
    -0.84
     azules
    -0.82
     balon
    -0.82
    ḇ
    -0.82
     carbone
    -0.81
     pik
    -0.81
     Polen
    -0.81
    POSITIVE LOGITS
     result
    4.44
    result
    3.45
     результате
    2.84
     consequence
    2.84
     resultado
    2.73
    Result
    2.72
    結果
    2.50
     Result
    2.48
    Consequently
    2.45
     consecuencia
    2.38
    Activations Density 0.041%

    No Known Activations