© 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. 50183
    Prev
    Next
    INDEX
    Explanations

    how someone feels

    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
    營業
    -0.81
    нка
    -0.79
     archers
    -0.78
     שיש
    -0.76
    fo
    -0.76
    inee
    -0.76
     Pol
    -0.72
    ī
    -0.71
    ach
    -0.70
     洛
    -0.69
    POSITIVE LOGITS
     feel
    2.13
     feelings
    1.88
     feeling
    1.80
     FEEL
    1.59
    Feel
    1.58
     feels
    1.52
     felt
    1.48
    feeling
    1.45
    感觉
    1.38
     чув
    1.38
    Activations Density 0.019%

    No Known Activations