© 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. 39361
    Prev
    Next
    INDEX
    Explanations

    medical, technical, and abstract concepts

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

    technical terminology related to computer systems, mathematics, and engineering.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on specialized technical nouns and terminology (e.g. “telecommunications,” “service,” “provider,” “subscriber,” “network”) typically used in formal or domain-specific descriptions.

    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
    ようになった
    -1.01
    ariest
    -0.98
     time
    -0.97
     US
    -0.93
     Stufen
    -0.93
     type
    -0.91
    berra
    -0.91
     confirmed
    -0.90
     kind
    -0.90
    antiago
    -0.90
    POSITIVE LOGITS
     Kasus
    1.11
    Buat
    1.09
     באמצעות
    1.09
     með
    1.00
    Ukuran
    0.99
    ▃▃
    0.98
    Makanan
    0.98
     with
    0.98
    Nro
    0.98
    Informasi
    0.97
    Activations Density 0.181%

    No Known Activations