© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8526
    Prev
    Next
    INDEX
    Explanations

    translation and literal meanings

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

    The neuron fires on infrequent foreign or specialized terms—especially proper names and culturally specific words.

    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
     primaries
    0.56
     STEM
    0.55
     mAb
    0.55
     AgNO
    0.54
    lení
    0.52
     represented
    0.52
    enek
    0.52
    ₓ
    0.52
     Therapie
    0.52
     ∑
    0.50
    POSITIVE LOGITS
     literalmente
    1.00
    literally
    0.90
     ungef
    0.86
    roughly
    0.81
     literally
    0.80
    translated
    0.80
     буквально
    0.80
     Literally
    0.79
     translated
    0.72
    pronounced
    0.71
    Activations Density 0.253%

    No Known Activations