Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 9
    Prev
    Next
    INDEX
    Explanations

    the neuron is looking for URLs and online web addresses.

    oai_token-act-pair · gpt-5-nanoTriggered by @aardvarkkr

    The neuron is keyed to detecting web addresses (e.g. the “www” token in URLs).

    oai_token-act-pair · o4-miniTriggered by @aardvarkkr
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post
    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
    ч
    0.42
    ра
    0.40
    пи
    0.39
    一百
    0.38
    тся
    0.36
     muest
    0.36
    か
    0.36
    ត្
    0.35
     perhitungan
    0.35
    сы
    0.34
    POSITIVE LOGITS
    <0x0D>
    0.47
     a
    0.43
     
    0.40
     for
    0.39
    iro
    0.39
     during
    0.39
    ing
    0.38
     by
    0.36
     at
    0.36
    nyder
    0.35
    Activations Density 0.001%

    No Known Activations