© 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. 907
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on the first substantive token (the first “real” word) immediately following a sentence boundary.

    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
    În
    0.70
    Asimismo
    0.68
    💒
    0.68
    ➝
    0.68
    »،
    0.66
    🏬
    0.66
    <0xE3>
    0.65
     সংগীত
    0.65
    functie
    0.64
    🏢
    0.64
    POSITIVE LOGITS
     G
    0.96
     J
    0.94
     L
    0.94
     K
    0.92
     R
    0.91
     those
    0.91
     M
    0.91
     T
    0.89
     F
    0.88
     other
    0.87
    Activations Density 6.085%

    No Known Activations