© 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. 31-GEMMASCOPE-2-RES-16K
    7. 111
    Prev
    Next
    INDEX
    Explanations

    This neuron flags HTTP/HTML attribute and header names (e.g. “href,” “host,” “referrer,” etc.).

    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
     सुमारे
    0.53
     étage
    0.52
    ্যালেঞ্জ
    0.52
     अल्को
    0.51
    舢
    0.51
    ्हान
    0.50
    quin
    0.49
    stituting
    0.49
     व्हाउचर
    0.48
    czyn
    0.48
    POSITIVE LOGITS
     "
    1.59
    ("
    1.47
    ="
    1.45
     '
    1.32
    ('
    1.23
     “
    1.19
     "_
    1.19
     "'
    1.19
    ='
    1.18
    ":"
    1.16
    Activations Density 0.025%

    No Known Activations