© 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. 14086
    Prev
    Next
    INDEX
    Explanations

    numbers stations

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

    The neuron spotlights the main topic word (a central content noun) in each 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
    ଅ
    0.98
     engaged
    0.83
     clin
    0.80
    /**
    0.77
    engage
    0.76
     engage
    0.74
    蝉
    0.74
    וע
    0.72
     benchmarks
    0.72
     emergencies
    0.71
    POSITIVE LOGITS
     ursprünglich
    0.92
     fün
    0.86
     decía
    0.83
     zunächst
    0.83
     berühm
    0.81
    stufe
    0.80
    ität
    0.80
     erste
    0.78
     erster
    0.78
     Russische
    0.78
    Activations Density 0.001%

    No Known Activations