© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9072
    Prev
    Next
    INDEX
    Explanations

    injection

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

    The neuron fires strongly on mentions of injectable medical treatments (injections, injected, injection procedures, etc.).

    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
    籀
    0.58
    鼾
    0.56
     Schwe
    0.52
    chnitten
    0.50
     સૂ
    0.49
    Exporter
    0.49
    xk
    0.49
     sweatshirts
    0.48
    fficacy
    0.48
    晎
    0.47
    POSITIVE LOGITS
     injection
    2.42
     Injection
    2.38
     inject
    2.31
     injections
    2.31
     Inject
    2.31
     injecting
    2.25
    Inject
    2.23
    inject
    2.22
     injector
    2.20
    injection
    2.17
    Activations Density 0.131%

    No Known Activations