© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7846
    Prev
    Next
    INDEX
    Explanations

    depressive disorder or symptoms

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

    medical terms related to depression and depressive disorders.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on words relating to depression (e.g. “depressive,” “depression,” “major depressive disorder,” 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_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
     of
    -2.03
     to
    -1.97
     who
    -1.72
    atrician
    -1.66
     respective
    -1.65
     selaku
    -1.61
    ifornie
    -1.56
    asanjo
    -1.54
    phrag
    -1.54
     Whether
    -1.52
    POSITIVE LOGITS
    .
    1.70
     Menschheit
    1.52
    贬
    1.49
     and
    1.48
     tiens
    1.44
     vrienden
    1.41
     boya
    1.41
     javas
    1.38
     zwarte
    1.38
    鹩
    1.38
    Activations Density 0.045%

    No Known Activations