© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 168
    Prev
    Next
    INDEX
    Explanations

    Feature list

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

    The neuron strongly activates on period‐type punctuation (single “.” or runs of dots), i.e. sentence‐ending “.” tokens.

    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
     maail
    0.44
     befri
    0.42
     volonté
    0.42
     magasins
    0.42
     feste
    0.42
    ḕ
    0.42
     þe
    0.42
     entretenimiento
    0.42
     termo
    0.41
     semblance
    0.41
    POSITIVE LOGITS
                         
    0.69
                       
    0.65
                   
    0.64
                        
    0.64
                     
    0.64
                            
    0.63
    ................
    0.63
                      
    0.62
                  
    0.62
                          
    0.62
    Activations Density 0.189%

    No Known Activations