© 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. 6466
    Prev
    Next
    INDEX
    Explanations

    multi-lingual contexts

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

    The neuron detects non-Latin script characters (e.g. Japanese/Kanji, Kana, and other similar script symbols).

    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
    بالإنجليزية
    1.07
    銛
    1.07
    Methylsulfanyl
    1.06
    MaxIntensity
    1.02
    Celltype
    1.00
    mergeddata
    1.00
    ﺔ
    1.00
    Regardless
    0.94
    Quantitative
    0.93
    MinIntensity
    0.93
    POSITIVE LOGITS
     olmak
    1.16
     için
    1.12
    의
    1.11
     olan
    1.09
    을
    1.06
    에서
    1.05
    를
    1.05
     veya
    1.03
     daha
    1.02
     ile
    1.01
    Activations Density 0.027%

    No Known Activations