© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2594
    Prev
    Next
    INDEX
    Explanations

    psychological, intellectual, and medical conditions

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

    The neuron fires on mentions of specific medical conditions or diseases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    지컬
    0.65
    葫
    0.65
    မီ
    0.64
     തു
    0.63
     दशमलव
    0.63
    邀
    0.62
     ফৌজ
    0.62
     Buccaneers
    0.60
    堪
    0.59
     scum
    0.59
    POSITIVE LOGITS
     idiopathic
    1.59
     syndrome
    1.38
     syndromes
    1.36
     hypothyroidism
    1.25
     pancreatitis
    1.21
     anorexia
    1.16
     Syndrome
    1.12
     síndrome
    1.12
     epilepsy
    1.11
     anemia
    1.11
    Activations Density 0.315%

    No Known Activations