© 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. 75464
    Prev
    Next
    INDEX
    Explanations

    empathy and apathy

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

    The neuron activates on words built from the “path/pathy” root that denote emotional feeling or engagement (e.g. empathy, empathize, empathetic, apathy, telepathic).

    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
    );
    -3.25
    -2.52
     alcune
    -2.23
    温和
    -2.20
    ";
    -2.20
     Should
    -2.20
     alcuni
    -2.19
     You
    -2.19
     ’
    -2.17
     These
    -2.14
    POSITIVE LOGITS
    geſ
    2.97
    2.91
    鬟
    2.55
    ﱠ
    2.34
    岽
    2.31
    CHREIB
    2.25
    ſſel
    2.23
    .
    2.20
    (?)
    2.19
     slapping
    2.14
    Activations Density 0.003%
    No Known Activations