© 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. 12000
    Prev
    Next
    INDEX
    Explanations

    amidst, amid, in, surrounded

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

    The neuron detects emphatic locative phrases that highlight centrality—e.g. “in the heart of,” “in the midst of,” or “in the middle of.”

    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
    MQ
    0.57
     Лига
    0.56
    IKO
    0.55
     Эн
    0.55
     MOU
    0.54
    Mq
    0.54
     গাড়ীতে
    0.54
    槓
    0.53
    টো
    0.52
     EQ
    0.52
    POSITIVE LOGITS
     midst
    1.65
     amidst
    1.25
     amid
    1.20
     chaos
    1.01
     turmoil
    0.98
     surrounded
    0.94
     وسط
    0.92
     Amid
    0.90
    Amid
    0.89
     가운데
    0.89
    Activations Density 0.190%

    No Known Activations