© 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. 11197
    Prev
    Next
    INDEX
    Explanations

    you still have

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

    The neuron strongly activates on terms related to transactions, deliveries, and logistics (e.g., “receive,” “deliver,” “payment,” “shipping,” “order”).

    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
     😍
    0.41
     আহ্বায়ক
    0.40
     informatics
    0.39
    *,
    0.39
    ꧂
    0.39
     psychiatric
    0.37
     chemotherapy
    0.37
     bioinformatics
    0.37
     cyberspace
    0.36
    。《
    0.36
    POSITIVE LOGITS
     opět
    0.51
    ⅼ
    0.46
    ſelf
    0.43
    再び
    0.40
    ſe
    0.40
    后者
    0.40
     yine
    0.39
     மீண்டும்
    0.39
    呲
    0.39
    plats
    0.38
    Activations Density 0.671%

    No Known Activations