© 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. 15823
    Prev
    Next
    INDEX
    Explanations

    black and white suspects

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

    The neuron fires strongly on the very first meaningful token in each new text segment or paragraph.

    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
     ford
    0.84
    Ford
    0.70
    ün
    0.68
     classifies
    0.67
    {
    0.66
    öll
    0.66
    Lemma
    0.64
     discriminate
    0.64
     underscore
    0.64
     classify
    0.63
    POSITIVE LOGITS
     informações
    0.84
    وية
    0.83
    佲
    0.79
    یل
    0.78
     informazioni
    0.78
     instalaciones
    0.77
     tertinggi
    0.77
     futebol
    0.77
     calendario
    0.77
     directorio
    0.76
    Activations Density 0.000%

    No Known Activations