© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8350
    Prev
    Next
    INDEX
    Explanations

    interns, composition, VB versions

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

    The neuron fires on tokens belonging to commercial or promotional content—especially URLs, brand or product names, and similar advertisement markers.

    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_24_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
    Compared
    0.92
    raspberry
    0.89
    ल
    0.89
    ying
    0.87
    Florence
    0.84
    顷
    0.83
    ри
    0.83
    Peru
    0.82
    র
    0.80
    europa
    0.80
    POSITIVE LOGITS
     /$
    0.82
     lifeline
    0.78
     सहमत
    0.77
     gallant
    0.76
     և
    0.74
     võivad
    0.74
     seminars
    0.73
     agrees
    0.71
     charities
    0.71
     bankers
    0.71
    Activations Density 0.000%

    No Known Activations