© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10385
    Prev
    Next
    INDEX
    Explanations

    She prefixes

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

    The neuron selectively activates on tokens beginning with the letters “she,” for example material or product names like shearling, sheathing, and sheets.

    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
    Hozz
    0.55
    نده
    0.52
    cesor
    0.52
    റ്റർ
    0.52
    ｾ
    0.51
    ittings
    0.50
    নীতির
    0.50
    ことも
    0.50
    掊
    0.50
    樍
    0.49
    POSITIVE LOGITS
     Ше
    0.92
     She
    0.77
    She
    0.73
     शे
    0.72
    pherd
    0.72
    SHE
    0.68
    pherds
    0.65
    anigans
    0.63
    lag
    0.61
    burne
    0.61
    Activations Density 0.119%

    No Known Activations