© 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. 93738
    Prev
    Next
    INDEX
    Explanations

    HTML structure and CSS content

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

    The neuron strongly activates on technical or metadata tokens—especially numbers, file‐ or code‐style identifiers, punctuation, and markup/HTML/CSS keywords.

    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
    abyrinth
    -0.77
     niedriger
    -0.70
    ISIONS
    -0.67
     memperoleh
    -0.67
    erunner
    -0.65
    coming
    -0.65
    Published
    -0.63
    chting
    -0.63
     term
    -0.62
     units
    -0.62
    POSITIVE LOGITS
    礼
    0.73
     sjø
    0.68
    禮
    0.66
     مك
    0.65
     anggota
    0.64
    FLOR
    0.64
    ikka
    0.63
     Florida
    0.63
    alanta
    0.63
    Mileage
    0.63
    Activations Density 0.074%

    No Known Activations