© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10552
    Prev
    Next
    INDEX
    Explanations

    non-english words and code

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

    The neuron strongly activates on numeric tokens and related punctuation (digits, dates, times, and numeric separators).

    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
    <start_of_image>
    1.52
    Coronavirus
    1.39
     కరో
    1.30
     코로나
    1.26
     coronavirus
    1.24
    coronavirus
    1.24
     коронави
    1.24
     கொரோ
    1.23
     कोरोनावायरस
    1.23
     Coronavirus
    1.20
    POSITIVE LOGITS
    🩶
    1.29
    🫡
    1.17
    🩷
    1.17
     AI
    1.05
     ChatGPT
    0.99
    🥹
    0.97
    🫰
    0.96
    🫤
    0.95
    🫶
    0.95
    🫠
    0.95
    Activations Density 0.099%

    No Known Activations