© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7182
    Prev
    Next
    INDEX
    Explanations

    adoption and foster care

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

    This neuron fires on tokens appearing in the movie‐plot summary section (i.e. narrative describing characters and their actions), and stays off elsewhere.

    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
     alloying
    0.60
     shim
    0.59
    锐
    0.56
     hémorro
    0.54
     breezy
    0.54
     ಕಡಿಮೆ
    0.53
    ഷ
    0.52
    ประตู
    0.52
    鉆
    0.52
     orgullo
    0.52
    POSITIVE LOGITS
     Adoption
    1.77
     adoption
    1.59
     adoptive
    1.59
    adoption
    1.57
     foster
    1.53
     orphan
    1.48
     orphanage
    1.48
    adopt
    1.42
    Adopt
    1.41
     adop
    1.38
    Activations Density 0.340%

    No Known Activations