© 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. 98521
    Prev
    Next
    INDEX
    Explanations

    comprehensive: [topic]

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

    This neuron fires strongly on the word “comprehensive” (in any casing), especially when it appears as part of a title or heading.

    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
     Their
    -0.94
     invitado
    -0.91
     širo
    -0.91
     Спо
    -0.91
     Ahora
    -0.91
     cómo
    -0.91
     vaše
    -0.90
    Če
    -0.90
    ต่อไป
    -0.90
     šte
    -0.88
    POSITIVE LOGITS
     approach
    1.67
     coverage
    1.40
     package
    1.34
     solution
    1.27
    )”
    1.25
     understanding
    1.22
    approach
    1.12
    解决方案
    1.07
    Approach
    1.06
     brune
    1.05
    Activations Density 0.027%

    No Known Activations