© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33125
    Prev
    Next
    INDEX
    Explanations

    Assisted Reproductive, Systems Market, billing solutions

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

    The neuron fires on domain‐specific business and technology report headings—words like “healthcare,” “technology,” “industry/industries,” “market,” “global,” “ART,” “systems,” etc.

    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
     lámparas
    -1.54
     gewüns
    -1.45
     algodón
    -1.37
     Bewußt
    -1.34
     šaty
    -1.32
     ſon
    -1.31
     červená
    -1.31
    tôi
    -1.30
    nitř
    -1.30
    ченная
    -1.27
    POSITIVE LOGITS
     in
    1.52
     for
    1.49
     is
    1.25
     &
    1.16
    ?
    1.13
     In
    1.10
     компо
    1.09
     llegando
    1.08
     global
    1.07
     \&
    1.07
    Activations Density 0.009%

    No Known Activations