© 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. 565
    Prev
    Next
    INDEX
    Explanations

    abbreviations and code structure

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

    The neuron fires on tokens that are capitalized acronyms, file‐type extensions, or proper‐name entities.

    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
     pó
    -1.06
    áns
    -1.05
    さてさて
    -1.00
    ネットで
    -0.99
    スポンサーリンク
    -0.99
    Со
    -0.97
     Beyer
    -0.96
    ises
    -0.96
     bym
    -0.95
     charbon
    -0.94
    POSITIVE LOGITS
     which
    1.38
    igail
    1.12
     Hinsicht
    0.96
     árvores
    0.93
    acamata
    0.92
    jutant
    0.91
    nolia
    0.91
    djang
    0.90
    keye
    0.90
    hob
    0.89
    Activations Density 0.107%

    No Known Activations