© 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. 10-GEMMASCOPE-RES-131K
    7. 71100
    Prev
    Next
    INDEX
    Explanations

    transl, transliteration patterns

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

    The neuron is firing on mid-length subword stems and acronyms (e.g. “transl” in transliteration, “alkal” in alkaloid, “ISC,” or the Thai character token “ท”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     cleanse
    -2.47
     сумка
    -2.44
    “
    -2.42
     {
    -2.41
    EN
    -2.36
     —
    -2.30
     Does
    -2.28
     However
    -2.28
     wachsen
    -2.28
    J
    -2.25
    POSITIVE LOGITS
    伈
    2.69
    旆
    2.61
     nadru
    2.56
    saya
    2.53
    齜
    2.50
     モード
    2.34
    buon
    2.22
    谆
    2.20
    dolce
    2.19
     安卓
    2.19
    Activations Density 0.011%

    No Known Activations