© 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. 6095
    Prev
    Next
    INDEX
    Explanations

    last president

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

    This neuron consistently activates on the very first meaningful token of each segmented passage.

    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
    ä
    0.87
    å
    0.84
    lish
    0.83
    na
    0.80
     Cla
    0.78
    lll
    0.78
    asjon
    0.78
    ilda
    0.77
    é
    0.77
    lin
    0.77
    POSITIVE LOGITS
     penchant
    0.89
     Ghanaian
    0.77
     AMOLED
    0.77
    躓
    0.77
     gastro
    0.76
     convolutional
    0.76
     envo
    0.75
     fermionic
    0.75
     commandment
    0.75
     fintech
    0.74
    Activations Density 0.000%

    No Known Activations