© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13294
    Prev
    Next
    INDEX
    Explanations

    ret- prefix

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

    The neuron fires on mentions of the topical retinoid medication “Retin-A.”

    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
    بخ
    0.60
    दूसरे
    0.59
     ગાંધી
    0.58
    テープ
    0.57
    NEY
    0.57
    0.57
    Poke
    0.57
    폭
    0.57
    넣
    0.57
    昅
    0.57
    POSITIVE LOGITS
     ret
    1.23
     Ret
    1.22
     retin
    1.02
    Ret
    1.00
     reti
    0.87
    ret
    0.84
     RET
    0.82
     retard
    0.81
     퇴
    0.77
    RET
    0.75
    Activations Density 0.100%

    No Known Activations