© 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. 8075
    Prev
    Next
    INDEX
    Explanations

    numbers and scientific notation

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

    The neuron is detecting HTML superscript tags (e.g. “<sup>”) that mark superscript content.

    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
     surprisingly
    0.76
    ects
    0.66
     nCount
    0.66
    াত
    0.64
    ➤
    0.64
    like
    0.64
    雫
    0.64
    ▷
    0.63
     cush
    0.63
     dashed
    0.61
    POSITIVE LOGITS
     ország
    0.76
     تازه
    0.73
     Información
    0.72
     اخبار
    0.72
     પ્રથમ
    0.71
     ameryka
    0.71
     Público
    0.70
     영국
    0.70
    英国
    0.69
     noticias
    0.69
    Activations Density 0.000%

    No Known Activations