© 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. 34-GEMMASCOPE-RES-131K
    7. 92652
    Prev
    Next
    INDEX
    Explanations

    reply links

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

    Explanation of neuron 4 behavior: the main thing this neuron does is detect the right single-quote/curly apostrophe character in 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_34/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
    さんです
    -0.96
    臂
    -0.85
     created
    -0.84
    bonsoir
    -0.78
     more
    -0.77
     selatan
    -0.77
     out
    -0.75
     information
    -0.74
     Cama
    -0.74
    🤎
    -0.74
    POSITIVE LOGITS
    LikeLike
    1.37
    Reply
    1.11
     Reply
    1.10
     reply
    0.98
    lognese
    0.90
            
    0.90
    fahrzeuge
    0.90
    ⚀
    0.90
              
    0.88
    reply
    0.87
    Activations Density 0.003%

    No Known Activations