© 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. 99844
    Prev
    Next
    INDEX
    Explanations

    erectile dysfunction

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

    medical terms related to erectile dysfunction.

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

    This neuron detects mentions of “erectile dysfunction.”

    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
    d
    -2.42
    o
    -2.34
     \"
    -2.34
    e
    -2.22
     thc
    -2.17
    y
    -2.16
    ，「
    -2.11
     «
    -2.09
    {
    -2.08
    ''
    -2.06
    POSITIVE LOGITS
     Không
    2.42
    にほんブログ村
    2.38
    that
    2.31
    </i>
    2.30
    迺
    2.23
     {
    2.22
     Outils
    2.22
    -“
    2.20
     Meilleures
    2.20
     که
    2.19
    Activations Density 0.001%

    No Known Activations