© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60085
    Prev
    Next
    INDEX
    Explanations

    feelings for someone

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

    The neuron detects first‐person expressions of personal feelings or emotional states (e.g., “I feel,” “I have feelings,” etc.).

    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
    finement
    -0.84
    рел
    -0.77
     commerces
    -0.76
     AIN
    -0.75
     milit
    -0.74
     عص
    -0.72
    urbs
    -0.71
     integrale
    -0.71
     remé
    -0.70
     socios
    -0.69
    POSITIVE LOGITS
     feelings
    3.39
     Feelings
    2.44
    feelings
    2.20
     Gefühle
    1.88
     sentimientos
    1.86
     gevoel
    1.59
     affections
    1.58
     чувства
    1.53
     feeling
    1.52
     sentimentos
    1.51
    Activations Density 0.018%

    No Known Activations