© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8947
    Prev
    Next
    INDEX
    Explanations

    a/an followed by noun

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

    The neuron is triggered by the causal/discourse connective phrase “as a result.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ガ
    0.68
    ifical
    0.63
    डु
    0.61
     অদ্ভুত
    0.61
     ग्ल
    0.61
     চলিয়া
    0.60
    0.60
     生命
    0.59
    ଈ
    0.59
    گ
    0.58
    POSITIVE LOGITS
     result
    1.16
     consequence
    1.13
     precaution
    1.09
     reminder
    0.90
     consecuencia
    0.89
     rule
    0.87
     gevolg
    0.87
     conseguenza
    0.86
     følge
    0.86
     resultado
    0.86
    Activations Density 0.231%

    No Known Activations