© 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. 1507
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly selective for the bigram “windows installation.”

    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
    An
    0.77
    B
    0.77
    Ба
    0.75
    Al
    0.75
    M
    0.73
    L
    0.73
    ﻤ
    0.72
    J
    0.71
    E
    0.71
    Ar
    0.71
    POSITIVE LOGITS
     producten
    0.81
     zařízení
    0.79
     omdat
    0.77
     jenis
    0.76
     waardoor
    0.75
     produkter
    0.75
     ponieważ
    0.75
     waahanga
    0.74
     produse
    0.74
     ürün
    0.73
    Activations Density 1.074%

    No Known Activations