© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9895
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with parentheses

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

    This neuron detects HTML (or XML) character entity references (e.g. ", &,  , numeric entities).

    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>
    0.71
     Beginner
    0.57
     Strength
    0.56
     PAK
    0.55
     \}$
    0.54
     beginner
    0.54
     strength
    0.53
     пам
    0.53
     문제입니다
    0.52
     $\
    0.52
    POSITIVE LOGITS
    ("
    0.62
    Omega
    0.62
    )^(
    0.61
    増
    0.61
    伴
    0.60
    (:,
    0.59
    悦
    0.59
    >)</
    0.59
    ^(
    0.58
    PROVID
    0.58
    Activations Density 0.031%

    No Known Activations