© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6711
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

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

    The neuron detects HTML (or XML) character/entity references—e.g. sequences starting with “&” (or “&#”) and ending with “;”.

    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
    🅘
    0.66
     suburb
    0.62
    𝕙
    0.61
     compét
    0.59
     suburban
    0.59
    𝙧
    0.58
    🅷
    0.55
    ⁠
    0.55
    🛑
    0.54
     insur
    0.53
    POSITIVE LOGITS
    @
    0.67
    Ç
    0.63
     %
    0.62
    ()*
    0.57
    '@
    0.56
    %
    0.55
     '@
    0.55
     +#
    0.55
    .#
    0.54
    +'
    0.54
    Activations Density 0.104%

    No Known Activations