© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14199
    Prev
    Next
    INDEX
    Explanations

    numbers in dates

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

    The neuron activates on standalone numeric tokens, flagging digits or numbers in the text.

    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
    ି
    -1.56
     partecipa
    -1.55
    ſes
    -1.52
    oncesto
    -1.47
    一开始
    -1.46
    meneu
    -1.42
     ujedno
    -1.42
    Цели
    -1.41
     понравился
    -1.41
    蹂
    -1.40
    POSITIVE LOGITS
    '
    2.00
    .
    1.73
              
    1.72
    \
    1.70
            
    1.70
     "
    1.67
     it
    1.62
                    
    1.53
               
    1.49
                      
    1.47
    Activations Density 0.068%

    No Known Activations