© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9925
    Prev
    Next
    INDEX
    Explanations

    Emphasis on critical effects

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

    The neuron is sensitive to economic and financial terminology, especially words related to monetary policy and macroeconomic topics.

    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_31_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
    ־
    0.96
     hereinafter
    0.93
    hereinafter
    0.90
    Notwithstanding
    0.88
     nonché
    0.87
    我在
    0.85
     admittedly
    0.85
    笔者
    0.84
    につきまして
    0.83
    –
    0.80
    POSITIVE LOGITS
     đc
    1.55
     ppl
    1.49
    
    1.41
     społ
    1.39
     expts
    1.36
     
    1.35
     govt
    1.34
     probs
    1.33
     =&
    1.23
     -&
    1.23
    Activations Density 0.066%

    No Known Activations