© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66435
    Prev
    Next
    INDEX
    Explanations

    Bollywood Fashion

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

    The neuron fires on non-English (foreign) words—especially accented or non-ASCII tokens—i.e. it marks translated text in other languages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ɞ
    -1.28
    Kondisi
    -1.13
     täglichen
    -1.13
    siapkan
    -1.09
    שים
    -1.08
     burbu
    -1.06
    timme
    -1.05
     communiquez
    -1.05
    bagai
    -1.04
    tentu
    -1.03
    POSITIVE LOGITS
     you
    1.54
     your
    1.44
    ꈍ
    1.12
    ῃ
    1.07
    ‑
    1.05
    aimerais
    1.05
    спомина
    1.04
    get
    1.04
    your
    1.03
    LUT
    1.03
    Activations Density 0.029%

    No Known Activations