© 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. 24-GEMMASCOPE-2-RES-16K
    4. 14172
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

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

    the neuron identifies rare or distinctive tokens—especially proper names or uncommon 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_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
    ا
    0.75
    ชัย
    0.68
     collaborator
    0.68
     a
    0.65
    uwa
    0.63
    Open
    0.62
     collaboration
    0.62
    יה
    0.61
    Omn
    0.61
    :'
    0.59
    POSITIVE LOGITS
     природе
    0.87
    另一方面
    0.86
     Bereichen
    0.85
    ,’’
    0.84
    brochen
    0.84
     месту
    0.84
     память
    0.83
     Bereiche
    0.83
     Estud
    0.80
     очень
    0.79
    Activations Density 0.000%

    No Known Activations