© 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. 34-GEMMASCOPE-RES-131K
    7. 80717
    Prev
    Next
    INDEX
    Explanations

    expressions of smiling or grinning

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     alegría
    -0.88
     scow
    -0.83
     cack
    -0.81
     चे
    -0.79
    face
    -0.76
    uję
    -0.76
     frowning
    -0.75
    ufs
    -0.75
     giggling
    -0.73
    льного
    -0.72
    POSITIVE LOGITS
    --;
    0.98
     lop
    0.96
     rue
    0.94
    tował
    0.88
    Läs
    0.85
     作り方
    0.85
     faintly
    0.82
     reassuring
    0.82
     wicked
    0.82
    𝖗
    0.81
    Activations Density 0.004%

    No Known Activations