© 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. 13513
    Prev
    Next
    INDEX
    Explanations

    breast milk and dairy

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

    The neuron primarily detects references to breasts and related lactation terms (e.g. bra, breast, nursing, milk).

    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
     Ubuntu
    0.61
    otá
    0.61
    hbase
    0.59
     वर्ण
    0.58
     ஜன
    0.58
     Wanderers
    0.56
     வயி
    0.55
    蕪
    0.55
     Regist
    0.55
     HBase
    0.54
    POSITIVE LOGITS
     milk
    2.36
    乳
    2.31
    milk
    2.22
    Milk
    2.22
     Milk
    2.14
     乳
    2.13
     breast
    2.09
    Breast
    2.09
     молоко
    2.09
     Breast
    2.03
    Activations Density 0.282%

    No Known Activations