© 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. 5288
    Prev
    Next
    INDEX
    Explanations

    replacing phrases like "such as"

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

    The neuron activates strongly on words and phrases used in online gambling or casino contexts—e.g. roulette, slot, bonus, wager, jackpot, casino, deposit, etc.

    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
    жность
    0.64
     phylogeny
    0.63
     FERC
    0.60
     NADPH
    0.59
     противоре
    0.59
     NDVI
    0.57
    交通事故
    0.56
     INSTIT
    0.56
     adsorbent
    0.56
     mtDNA
    0.55
    POSITIVE LOGITS
     ribu
    0.63
    been
    0.60
    ruari
    0.59
    York
    0.59
     числі
    0.59
     been
    0.58
     світу
    0.56
     conjunction
    0.55
     york
    0.55
     York
    0.55
    Activations Density 0.324%

    No Known Activations