© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14969
    Prev
    Next
    INDEX
    Explanations

    performance, benefits, increased, typically

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

    This neuron detects key nouns and numerals used to report diagnostic findings or quantities in medical imaging contexts.

    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
     ١
    0.84
    /
    0.82
     +
    0.79
    த்தினை
    0.78
     ऑफिसियल
    0.76
     нашего
    0.76
     INCLUDING
    0.76
     BOTH
    0.74
     вашего
    0.74
     commenced
    0.73
    POSITIVE LOGITS
     typically
    0.88
    往往
    0.88
     automakers
    0.82
    typically
    0.81
     policymakers
    0.80
    亟
    0.80
     lawmaker
    0.78
     often
    0.75
     genellikle
    0.75
     अहम
    0.75
    Activations Density 0.007%

    No Known Activations