© 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. 11486
    Prev
    Next
    INDEX
    Explanations

    php class definitions

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

    The neuron is detecting mentions of social‐media platforms (e.g. Facebook, Instagram, Twitter, Google+) or their URLs.

    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
    <0x0D>
    0.67
     Announces
    0.57
     Applies
    0.52
    😸
    0.52
    Wnd
    0.51
     Warcraft
    0.51
     精
    0.51
    可行
    0.50
    「
    0.50
     applies
    0.50
    POSITIVE LOGITS
     সৃষ্টি
    0.60
     creations
    0.60
     cread
    0.59
     cockpit
    0.57
     auctor
    0.57
     created
    0.57
    Created
    0.57
     писатель
    0.57
    斻
    0.57
     Creation
    0.55
    Activations Density 0.005%

    No Known Activations