© 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. 10879
    Prev
    Next
    INDEX
    Explanations

    state abbreviations

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

    This neuron is essentially inactive—it doesn’t reliably fire on any text pattern.

    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
     bús
    -1.32
    THEY
    -1.23
     cheia
    -1.23
    ༈
    -1.21
     mág
    -1.21
    ggies
    -1.21
    และ
    -1.19
    ⎔
    -1.16
     jugu
    -1.16
    ☫
    -1.16
    POSITIVE LOGITS
     While
    1.13
     Numerous
    1.12
     or
    1.09
     F
    1.09
     at
    1.07
     while
    1.05
     What
    1.05
     Even
    1.03
     Although
    1.02
    While
    1.00
    Activations Density 0.002%

    No Known Activations