© 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. 119277
    Prev
    Next
    INDEX
    Explanations

    English rock bands, Austrian neurologists, American premium brands, animated comedy series

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

    This neuron detects the “is a [descriptor]” definitional phrase that introduces an entity’s key attributes (e.g. “is a Japanese multinational conglomerate corporation headquartered in Tokyo”).

    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
     only
    -1.21
     at
    -1.20
     one
    -1.12
     so
    -1.11
     in
    -1.05
     provided
    -1.05
     like
    -1.04
     with
    -1.04
     without
    -1.02
     every
    -1.02
    POSITIVE LOGITS
     brune
    1.19
     ........
    1.18
     ..........
    1.16
     sentiers
    1.15
    などが
    1.14
    饸
    1.14
    鵙
    1.12
    ౮
    1.10
    ___________
    1.09
     Dinas
    1.09
    Activations Density 0.349%

    No Known Activations