© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84872
    Prev
    Next
    INDEX
    Explanations

    HTML DOCTYPE declarations

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

    The neuron is a slash detector, firing on “/” or “//” tokens (e.g. in URLs, MIME types, DOCTYPE declarations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impre
    -0.72
     Galileo
    -0.71
     RTX
    -0.70
    SeekBar
    -0.69
     Wake
    -0.68
     unproductive
    -0.68
    PROGRESS
    -0.67
     Mr
    -0.67
    casino
    -0.66
    owią
    -0.66
    POSITIVE LOGITS
    Standard
    0.73
     بوك
    0.65
     Langen
    0.65
    Gret
    0.64
    isAdmin
    0.62
    マイズ
    0.62
     Babcock
    0.62
    ਤੀ
    0.61
     СТ
    0.61
    Story
    0.60
    Activations Density 0.061%

    No Known Activations