© 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. 9444
    Prev
    Next
    INDEX
    Explanations

    The neuron fires most strongly on rare or specialized tokens—uncommon words, proper names, and infrequent foreign or technical terms.

    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
    팅
    0.81
     DCC
    0.77
     McC
    0.75
     CCP
    0.75
    綱
    0.74
    스
    0.73
    부산
    0.73
    ⒋
    0.72
     OT
    0.71
    BUT
    0.71
    POSITIVE LOGITS
     modalCard
    0.75
     biodegradation
    0.75
     sparsity
    0.73
     getInput
    0.73
    ອງ
    0.72
     secondNumber
    0.71
     reductive
    0.70
     finiteness
    0.70
     बाथरूम
    0.69
     bridged
    0.69
    Activations Density 0.000%

    No Known Activations