© 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. 14852
    Prev
    Next
    INDEX
    Explanations

    list items followed by punctuation

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

    This neuron detects mentions of mental‐health problems or other personal trauma–related issues (e.g. depression, stress, abuse, bereavement).

    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
     dieses
    0.75
    ẃ
    0.66
     هذا
    0.65
    áticamente
    0.65
    ಲಿನ
    0.65
    mores
    0.64
    ımın
    0.64
    ítico
    0.64
     сучас
    0.64
    úst
    0.64
    POSITIVE LOGITS
     และ
    1.08
     そして
    0.97
     ،
    0.93
     ，
    0.93
     etc
    0.91
     প্রমুখ
    0.90
     그리고
    0.89
     ,
    0.88
     тощо
    0.88
     以及
    0.88
    Activations Density 0.658%

    No Known Activations