© 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. 76069
    Prev
    Next
    INDEX
    Explanations

    emotions and feelings

    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
    伤感
    -1.13
     gend
    -0.98
    છ
    -0.97
    foundland
    -0.91
    quele
    -0.90
     séjour
    -0.88
    pso
    -0.87
    igen
    -0.84
    view
    -0.83
    ियन
    -0.81
    POSITIVE LOGITS
     anger
    3.11
     sadness
    2.34
     angry
    2.33
     Anger
    2.22
     rage
    2.05
    Anger
    1.99
     sad
    1.84
     joy
    1.84
     fear
    1.82
     Sad
    1.79
    Activations Density 0.083%

    No Known Activations