© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2550
    Prev
    Next
    INDEX
    Explanations

    things, tasks, fair

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

    The neuron fires on medical or health‐care language—especially mentions of conditions, symptoms, treatments, side effects, or other clinical terminology.

    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_24_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
    0.73
     a
    0.60
     kidnapped
    0.56
     WAS
    0.55
     kidnapping
    0.55
     incessant
    0.55
     cowardly
    0.53
     paltry
    0.53
     autopsy
    0.52
     hiatus
    0.52
    POSITIVE LOGITS
    といった
    0.76
    。
    0.74
    。《
    0.72
    ។
    0.71
    ۔
    0.70
    และ
    0.67
    .。
    0.67
     。
    0.66
    。「
    0.65
    .<
    0.65
    Activations Density 0.000%

    No Known Activations