© 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. 944
    Prev
    Next
    INDEX
    Explanations

    that includes

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

    The neuron strongly activates on the sentence-initial demonstrative “That.”

    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
    $-
    0.68
    ic
    0.65
    про
    0.62
    ер
    0.62
    कर्मियों
    0.61
    с
    0.60
    $.}
    0.60
    спа
    0.59
    ڤ
    0.59
    channels
    0.59
    POSITIVE LOGITS
    zelfde
    1.36
     pesky
    1.27
     факт
    0.96
     fateful
    0.95
     same
    0.94
     moment
    0.92
     particular
    0.90
     bastion
    0.89
     bastard
    0.88
     horrid
    0.87
    Activations Density 0.393%

    No Known Activations