© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5613
    Prev
    Next
    INDEX
    Explanations

    formal situations

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

    The neuron strongly activates on occurrences of the word “official,” marking explicit official‐status or disclaimer labels.

    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
     wenige
    0.62
    ूरी
    0.61
    Cal
    0.59
    arma
    0.58
    Ꭿ
    0.57
    adro
    0.57
    Alle
    0.57
    𝒶
    0.56
    ad
    0.55
    alles
    0.55
    POSITIVE LOGITS
     official
    1.76
     Official
    1.70
     официа
    1.61
     Официа
    1.59
     OFFICIAL
    1.50
     officially
    1.48
     Officially
    1.46
     رسمی
    1.45
     oficial
    1.45
     resmi
    1.44
    Activations Density 0.114%

    No Known Activations