© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10321
    Prev
    Next
    INDEX
    Explanations

    cisgender identity and diagnoses

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

    This neuron is sensitive to numerical and measurement expressions (e.g. numbers, units, “Per Inch”).

    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
    𝒽
    0.78
     pleinement
    0.78
     було
    0.75
    ಭ
    0.75
    졌
    0.74
    大数据
    0.74
     resampling
    0.73
    NJ
    0.71
    丰富的
    0.71
    fungsi
    0.71
    POSITIVE LOGITS
     marketable
    0.70
    ן
    0.70
     hinter
    0.66
     medically
    0.66
     चाहें
    0.65
     maga
    0.65
     illnesses
    0.63
    সম্যান
    0.63
    ან
    0.62
     indicated
    0.61
    Activations Density 0.001%

    No Known Activations