© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1643
    Prev
    Next
    INDEX
    Explanations

    before diving

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

    The neuron fires on the final word of a sentence, i.e. the token immediately before the period (sentence end).

    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
    il
    0.89
    ک
    0.84
    mo
    0.81
    n
    0.80
    pe
    0.80
    ity
    0.78
    ious
    0.78
    ya
    0.74
    커
    0.73
    om
    0.73
    POSITIVE LOGITS
     alkaloids
    0.94
     longiore
    0.88
     Oilers
    0.87
     Oils
    0.85
    новения
    0.85
     EtOAc
    0.84
     succulent
    0.82
     olefins
    0.81
     policial
    0.80
     поез
    0.79
    Activations Density 0.000%

    No Known Activations