© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3642
    Prev
    Next
    INDEX
    Explanations

    pronouns

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

    This neuron strongly activates on the specific phrasing “health insurance across state lines.”

    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_24_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
     recollect
    1.03
     automate
    1.01
    s
    0.98
    のことを
    0.98
     stave
    0.97
    아야
    0.96
     outliers
    0.95
    说
    0.95
     attest
    0.95
    ियों
    0.94
    POSITIVE LOGITS
    ج
    1.24
    cule
    0.96
    pe
    0.93
     Excellency
    0.93
    fordshire
    0.91
    duled
    0.89
    bei
    0.88
    ുടെ
    0.87
     Highness
    0.85
    يئة
    0.84
    Activations Density 20.508%

    No Known Activations