© 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. 9992
    Prev
    Next
    INDEX
    Explanations

    instead of

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

    The neuron detects contrastive transition phrases—especially occurrences of “instead of.”

    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
     bahawa
    1.03
     Bn
    0.96
     Eğer
    0.95
    <unused21>
    0.91
     bhavanti
    0.89
     Satu
    0.88
     tambien
    0.88
    یف
    0.85
    Además
    0.84
     financière
    0.84
    POSITIVE LOGITS
    いた
    1.45
    り
    1.32
    ки
    1.30
    т
    1.29
    ছেন
    1.10
    ून
    1.10
    து
    1.08
    いました
    1.07
    hai
    1.05
    
    1.05
    Activations Density 0.035%

    No Known Activations