© 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. 36620
    Prev
    Next
    INDEX
    Explanations

    introducing a topic or subject

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

    The neuron fires on the first few content words of each new section or heading, effectively marking where a new post‐segment or title begins.

    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
    
    -0.96
     것입니다
    -0.92
     then
    -0.92
    isional
    -0.90
    weile
    -0.90
     też
    -0.89
    nologi
    -0.89
     others
    -0.89
     nawet
    -0.89
    谙
    -0.88
    POSITIVE LOGITS
     another
    1.67
     something
    1.49
    Another
    1.23
     again
    1.23
     how
    1.21
     nuovamente
    1.20
     our
    1.18
    haviours
    1.18
     novamente
    1.16
    Something
    1.13
    Activations Density 0.096%

    No Known Activations