© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45582
    Prev
    Next
    INDEX
    Explanations

    emoticons and punctuation

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

    The neuron is detecting smiley‐style emoticons, particularly the “)” in faces like “:)”.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    '
    -1.68
     spannend
    -1.63
     combat
    -1.57
     argentinos
    -1.55
     venezol
    -1.52
     spørsmål
    -1.47
     incessantly
    -1.46
     preescolar
    -1.46
    -
    -1.44
    TotalPrice
    -1.41
    POSITIVE LOGITS
    </td>
    2.41
    ");
    2.05
    </h5>
    1.93
     }));
    1.91
    }),
    
    1.88
    ")));
    1.77
    ueroa
    1.74
    %")
    1.70
     }),
    1.70
     bVar
    1.68
    Activations Density 0.011%

    No Known Activations