© 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. 5564
    Prev
    Next
    INDEX
    Explanations

    filling in blanks or placeholders

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

    The neuron responds to tokens that are uppercase or capitalized sequences representing brand names, product names, or organizational acronyms.

    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
    xmax
    0.60
    GPa
    0.60
    ሰው
    0.60
    例
    0.60
    maskedTextBox
    0.59
    शूट
    0.59
     جوړونکی
    0.58
    นคร
    0.57
    ালক
    0.57
    াতিক
    0.56
    POSITIVE LOGITS
     it
    0.78
     of
    0.77
     if
    0.70
    it
    0.66
     to
    0.63
     arred
    0.62
     you
    0.61
     wohn
    0.60
     —
    0.58
     australia
    0.58
    Activations Density 0.007%

    No Known Activations