© 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. 8087
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on formal, factual content words—technical or domain-specific terms and proper nouns (e.g. research, degree, systems, equity, parking, climate)—marking passages with informational or analytical language.

    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
    k
    1.03
    l
    0.93
    b
    0.88
     cordless
    0.85
    el
    0.84
    t
    0.84
    K
    0.83
    j
    0.83
    ot
    0.82
    lly
    0.81
    POSITIVE LOGITS
     údaje
    0.83
     könne
    0.83
     нескольких
    0.82
     некоторы
    0.82
    সীম
    0.79
     sommige
    0.79
     وهذا
    0.78
     menikmati
    0.78
     μια
    0.77
     spesies
    0.77
    Activations Density 1.632%

    No Known Activations