© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10480
    Prev
    Next
    INDEX
    Explanations

    http server and requests

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

    This neuron flags occurrences of the “http” or “HTTP” protocol token (i.e. parts of URLs or HTTP requests).

    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
    ecimiento
    0.61
    缱
    0.59
     Moreau
    0.58
     warmed
    0.57
    iteits
    0.55
     enquire
    0.55
     fadeInLeft
    0.54
     retorn
    0.54
     celestial
    0.53
     Coefficients
    0.53
    POSITIVE LOGITS
    olium
    0.62
    BH
    0.54
    冀
    0.53
     ॥
    0.52
    zine
    0.51
    through
    0.51
    PPI
    0.50
    abul
    0.50
    bür
    0.50
    inery
    0.50
    Activations Density 0.030%

    No Known Activations