© 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. 10240
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on the term “Upgrade” when it’s used as a call to action in promotional or subscription‐upgrade contexts.

    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
    است
    0.54
    ໃຫ້
    0.53
    Paragraph
    0.50
    від
    0.50
    合せ
    0.50
    accord
    0.50
    Sach
    0.50
    让
    0.50
    ран
    0.49
    дать
    0.49
    POSITIVE LOGITS
     DAY
    0.64
     planar
    0.63
     Angus
    0.61
     Monsanto
    0.60
     Lionel
    0.60
    oky
    0.60
     Grenoble
    0.59
     Burns
    0.59
     Crisis
    0.59
     Kellogg
    0.59
    Activations Density 0.000%

    No Known Activations