© 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. 22-GEMMASCOPE-RES-131K
    7. 28159
    Prev
    Next
    INDEX
    Explanations

    web elements and content

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

    The neuron is spotting CSS class‐name fragments—especially BEM‐style identifiers with double underscores, hyphens, or numeric tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     marcher
    -0.96
    folie
    -0.93
     geografia
    -0.91
    cyklopedia
    -0.90
     palet
    -0.90
    perties
    -0.90
     bougies
    -0.89
     frequentemente
    -0.89
     fortemente
    -0.89
    LoadScene
    -0.89
    POSITIVE LOGITS
     aveva
    1.26
     ბ
    1.02
     ---
    1.00
     recibe
    0.96
     hatte
    0.93
     '-')
    0.92
    rou
    0.91
    agissait
    0.91
     UserDao
    0.90
     Sortiment
    0.90
    Activations Density 0.003%

    No Known Activations