© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3508
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the names of paid content-amplification networks (e.g. Taboola, Outbrain, Zemanta) and related channel identifiers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     unruly
    0.67
     nossas
    0.66
    targetContext
    0.65
     consecuencia
    0.65
     nosso
    0.64
     அவற்றை
    0.63
     commotion
    0.63
     stillness
    0.63
     nossos
    0.61
     '.';
    0.61
    POSITIVE LOGITS
    Their
    1.80
    their
    1.71
    他们的
    1.66
     Their
    1.63
     their
    1.61
    他們的
    1.55
     അവരുടെ
    1.52
     njihov
    1.49
     jejich
    1.48
     их
    1.45
    Activations Density 0.918%

    No Known Activations