© 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. 5120
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for legal‐style terminology—especially privacy, confidentiality, and binding contract 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
    }')
    0.74
    予測
    0.74
    内で
    0.70
     an
    0.69
     ficción
    0.69
     Verw
    0.68
    }\,\
    0.68
    澄
    0.68
    ション
    0.67
     Diakses
    0.66
    POSITIVE LOGITS
    㗊
    0.85
    faire
    0.75
    鸹
    0.75
    िंक
    0.74
    afe
    0.73
    ingin
    0.72
    嚴重
    0.72
    싹
    0.72
    手上
    0.71
     publicized
    0.71
    Activations Density 0.001%

    No Known Activations