© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70815
    Prev
    Next
    INDEX
    Explanations

    seeking information or past events

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

    The neuron fires on meta-discussion or discourse words (e.g. community, may, not, always, share, help, preference)—i.e. general polite/hedging and sharing-style language rather than content-specific terms.

    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
     communiquez
    -1.03
     áng
    -1.01
     savait
    -0.96
     будет
    -0.94
     dát
    -0.93
     intertw
    -0.91
     auta
    -0.90
    brities
    -0.90
     difer
    -0.89
    Cyfeiriadau
    -0.89
    POSITIVE LOGITS
     africain
    1.05
    ittin
    1.03
     sands
    1.03
     wśród
    0.97
     gyak
    0.97
     Ә
    0.97
     besitzen
    0.96
     рекомендую
    0.96
     actrice
    0.95
    ionych
    0.93
    Activations Density 0.103%

    No Known Activations