© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16365
    Prev
    Next
    INDEX
    Explanations

    often

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

    The neuron fires on tokens that appear at the very start of a sentence or clause (i.e. sentence-initial 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
    this
    0.91
    ↵
    0.91
    lot
    0.88
    I
    0.86
    1
    0.86
    2
    0.86
    Dia
    0.85
    std
    0.83
    4
    0.82
     цієї
    0.81
    POSITIVE LOGITS
     выпол
    0.92
     býval
    0.88
     След
    0.86
     clínicos
    0.86
     называют
    0.84
    ографи
    0.84
    ÕES
    0.80
     замы
    0.80
    бири
    0.77
    BESCHREIBUNG
    0.76
    Activations Density 0.000%

    No Known Activations