© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3887
    Prev
    Next
    INDEX
    Explanations

    dating apps, pass packets, executive tests, grooming products

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

    The main thing this neuron does is detect web URLs (links to websites).

    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
     -
    0.70
    .........
    0.61
     ,
    0.60
     during
    0.59
     =
    0.58
     ■
    0.58
    During
    0.57
    ■
    0.55
     :
    0.55
    Brand
    0.54
    POSITIVE LOGITS
     chatbots
    0.75
     formalized
    0.69
     احتجاج
    0.65
     इथे
    0.64
    образ
    0.64
     niches
    0.64
     miejsca
    0.63
     വിദ്യാ
    0.63
    াড়াও
    0.62
     diligent
    0.62
    Activations Density 0.008%

    No Known Activations