© 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. 12725
    Prev
    Next
    INDEX
    Explanations

    marketing, sales, american, women

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

    The neuron specializes in detecting parts of URLs and hyperlink tokens (i.e. web addresses or link fragments).

    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
     consented
    0.87
     psychopath
    0.84
    ل
    0.83
    م
    0.80
     rousing
    0.79
     haught
    0.77
     psychos
    0.77
     smugg
    0.76
     tycoon
    0.76
    ಶ್ಯ
    0.75
    POSITIVE LOGITS
    Gener
    0.86
    蒎
    0.84
    Harris
    0.74
    编制
    0.74
    在线
    0.73
    0
    0.73
    Reading
    0.72
    dream
    0.72
    Univers
    0.71
    ˚
    0.71
    Activations Density 0.000%

    No Known Activations