© 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. 90436
    Prev
    Next
    INDEX
    Explanations

    textual emotional expressions

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

    The neuron strongly activates on emotive pictorial cues—i.e. emoticons (like “:)”, “; )”, “🙂”) conveying tone or emotion.

    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
     on
    -2.11
     C
    -1.96
     R
    -1.90
     N
    -1.85
     L
    -1.85
     M
    -1.77
     F
    -1.77
     A
    -1.77
     E
    -1.74
     ,
    -1.74
    POSITIVE LOGITS
     verhind
    1.77
    舀
    1.74
     bourg
    1.71
     raccont
    1.71
     bén
    1.70
     perguntas
    1.69
     juſ
    1.69
     alpes
    1.67
    蹚
    1.66
     dhe
    1.66
    Activations Density 0.010%

    No Known Activations