© 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. 8805
    Prev
    Next
    INDEX
    Explanations

    straightforward approach

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

    The neuron consistently lights up on the word “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
     antig
    0.60
     Pell
    0.59
     averaging
    0.58
    ̿
    0.55
    <0xE4>
    0.53
     (-
    0.51
     negativa
    0.51
     indeterminate
    0.50
     ann
    0.50
     indeterm
    0.50
    POSITIVE LOGITS
     IncludeField
    0.66
     대해
    0.64
    檴
    0.64
     فرض
    0.62
    只有一个
    0.62
    いますが
    0.61
     पूरे
    0.61
     있지만
    0.59
     Цу
    0.59
     FRANK
    0.58
    Activations Density 0.000%

    No Known Activations