© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15812
    Prev
    Next
    INDEX
    Explanations

    morning or wrong

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

    The neuron fires on words of thanks, praise, or other exclamatory expressions of gratitude.

    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
     !!!!
    0.66
     WHICH
    0.65
     THE
    0.64
     THIS
    0.63
     !!!
    0.62
     ///
    0.62
     -
    0.61
     THEY
    0.61
     असिस्टेंट
    0.61
    /**
    0.60
    POSITIVE LOGITS
    ,
    1.27
    ،
    1.23
    ，
    1.06
    ፣
    0.98
    {,}
    0.95
    、
    0.94
    ,_
    0.90
    ,{\
    0.87
    ၊
    0.85
    ,<
    0.82
    Activations Density 0.195%

    No Known Activations