© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9520
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on salient content words—particularly key nouns and verbs—rather than on common function words.

    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
    论
    0.78
    tać
    0.75
    邇
    0.71
     कन
    0.69
    ereco
    0.68
    ంత్ర
    0.68
    ctree
    0.67
    ịa
    0.66
    บรร
    0.66
    环境保护
    0.66
    POSITIVE LOGITS
     douloureuse
    0.76
     Cela
    0.75
     Communists
    0.75
     Leth
    0.74
     Communist
    0.73
    յ
    0.73
     Antit
    0.72
     Cholesterol
    0.71
     Regist
    0.71
     Bahkan
    0.71
    Activations Density 0.259%

    No Known Activations