© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75263
    Prev
    Next
    INDEX
    Explanations

    dates with months

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

    The neuron fires on the metadata separators and numeric tokens used in date‐and‐time stamps (e.g. the "|" marker and adjoining digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Therefore
    -1.63
     semblent
    -1.55
    多かった
    -1.41
    ticularly
    -1.39
    ragende
    -1.35
     Kemudian
    -1.35
    をはじめ
    -1.35
     parecen
    -1.32
     všetko
    -1.32
    莇
    -1.30
    POSITIVE LOGITS
              
    1.52
                   
    1.48
    １
    1.47
    鸰
    1.45
        
    1.45
                    
    1.43
    re
    1.42
               
    1.41
    Ｎ
    1.39
     ostro
    1.37
    Activations Density 0.041%

    No Known Activations