© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40452
    Prev
    Next
    INDEX
    Explanations

    can't beat, pass up, go wrong

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

    The neuron strongly activates on short, common function words and grammatical “stop” words (e.g., pronouns, articles, prepositions, auxiliary words, and other frequent little words).

    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
     navigateur
    -1.61
    '';
    -1.52
    gebene
    -1.38
     turista
    -1.37
     conde
    -1.34
    
    -1.34
    퐼
    -1.31
     himſelf
    -1.30
     fundas
    -1.28
    somebody
    -1.28
    POSITIVE LOGITS
     greatest
    1.49
      
    1.43
     that
    1.42
     ist
    1.40
     better
    1.34
       
    1.33
    Println
    1.27
    E
    1.25
        
    1.25
     great
    1.23
    Activations Density 0.035%

    No Known Activations