© 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. 6671
    Prev
    Next
    INDEX
    Explanations

    start of an abstract

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

    The neuron is essentially inactive and does not respond to any patterns in the text.

    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
     photograph
    0.39
     FEES
    0.37
    ج
    0.37
     Thailand
    0.36
     Photograph
    0.35
    州市
    0.34
     Fees
    0.34
     thei
    0.34
     singer
    0.33
     PHE
    0.33
    POSITIVE LOGITS
     dessa
    0.38
    (){
    0.37
    OrCreate
    0.37
    (<
    0.36
    ItemSelected
    0.35
    HelloWorld
    0.34
     ඇති
    0.34
     এক্ষেত্রে
    0.34
    在這
    0.34
     existentes
    0.34
    Activations Density 0.001%

    No Known Activations