© 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. 5836
    Prev
    Next
    INDEX
    Explanations

    family and lifestyle terms

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

    This neuron activates on highly enthusiastic or emphatic expressions—especially excited, praise-laden language often marked with exclamation or superlative phrasing.

    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
    だが
    0.97
    Fuck
    0.93
     Obrigado
    0.91
    łem
    0.89
     Fuck
    0.86
    ようだ
    0.83
     ครับ
    0.79
     俺
    0.78
    ☭
    0.78
    俺
    0.77
    POSITIVE LOGITS
     kiddos
    1.46
     hubby
    1.36
     엄마
    1.30
     blogger
    1.30
     bloggers
    1.24
     girly
    1.23
     mama
    1.20
     Pinterest
    1.20
     blogging
    1.20
     pinterest
    1.19
    Activations Density 2.183%

    No Known Activations