© 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. 24-GEMMASCOPE-2-RES-16K
    7. 160
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron strongly activates on numeric tokens—especially multi‐digit sequences, version numbers, HTTP version strings, parameter values, etc.

    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
    কেমিক্যাল
    0.23
    DEPARTMENT
    0.22
    និច
    0.22
    )}_
    0.22
    setRoi
    0.21
    HOBBIT
    0.21
    setTime
    0.21
    tkWidget
    0.21
    ক্ষিপ্ত
    0.21
    covariant
    0.21
    POSITIVE LOGITS
    0.26
    i
    0.22
     Montreal
    0.21
     así
    0.21
     Sydney
    0.21
    ↵↵
    0.21
    兼容
    0.21
     Mumbai
    0.20
     concise
    0.20
     we
    0.20
    Activations Density 0.019%

    No Known Activations