© 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. 8582
    Prev
    Next
    INDEX
    Explanations

    Environmental, Social, Governance (ESG)

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

    The neuron responds strongly to English articles—especially “the” and “a.”

    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
    𝙩
    0.82
    𝙛
    0.79
    𝚐
    0.78
    𝙙
    0.71
    doll
    0.70
    freq
    0.66
    kala
    0.66
    rations
    0.66
    𝑪
    0.66
    backs
    0.66
    POSITIVE LOGITS
     ১২
    0.90
     promulg
    0.86
     prazo
    0.83
    Until
    0.82
     avendo
    0.82
     totalité
    0.80
    ካከል
    0.80
     spectacular
    0.80
     amplia
    0.79
     отсутствие
    0.79
    Activations Density 0.009%

    No Known Activations