© 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. 205
    Prev
    Next
    INDEX
    Explanations

    but, and

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

    The neuron strongly activates on expressions of praise or positive feedback (e.g. “Great video,” “Nice job,” “Superb article,” “I liked…”).

    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
    ,
    0.26
    0.22
    ),
    0.21
            
    0.21
    )
    0.21
    ()
    0.21
                          
    0.21
    0.21
    0.20
    [
    0.20
    POSITIVE LOGITS
     αλλά
    0.33
     but
    0.31
     लेकिन
    0.31
     אבל
    0.30
     pero
    0.29
     ولكن
    0.29
     protože
    0.29
     takže
    0.29
     क्योंकि
    0.27
     mutta
    0.27
    Activations Density 1.954%

    No Known Activations