© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8291
    Prev
    Next
    INDEX
    Explanations

    categorizing by attribute

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

    The neuron is triggered by uncommon, multi‐syllabic (i.e. unusually long or rare) words.

    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
     pesa
    0.62
     preferably
    0.55
     queda
    0.55
     方
    0.54
    āda
    0.54
     пап
    0.54
    ishan
    0.53
    nika
    0.52
     buka
    0.52
    呗
    0.52
    POSITIVE LOGITS
     appearance
    0.97
     stature
    0.95
    性質
    0.92
     size
    0.86
    性质
    0.86
    appearance
    0.80
     nature
    0.78
     effectiveness
    0.77
     intensity
    0.77
     structure
    0.75
    Activations Density 0.260%

    No Known Activations