© 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. 17
    Prev
    Next
    INDEX
    Explanations

    html code tags

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

    The neuron detects formatted dates (e.g. month names, commas, and year numbers).

    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
     equivari
    0.37
     FTIR
    0.37
     cláus
    0.37
    LOTREntity
    0.37
     تبدی
    0.34
    AsyncKeyState
    0.34
    
    0.34
    starcore
    0.34
     राहणार
    0.33
    屉
    0.33
    POSITIVE LOGITS
    ↵
    0.36
        
    0.36
    <
    0.36
     public
    0.34
      
    0.33
    <0xE3>
    0.33
    /**
    0.33
     中
    0.33
    Э
    0.32
    ion
    0.32
    Activations Density 0.406%

    No Known Activations