© 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. 9711
    Prev
    Next
    INDEX
    Explanations

    this + noun phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     will
    -1.14
     to
    -1.12
     would
    -1.11
     of
    -1.04
     most
    -1.02
    redientes
    -1.02
     is
    -1.01
     verwijzen
    -1.00
     zapew
    -0.94
     next
    -0.93
    POSITIVE LOGITS
    好像
    1.26
    这些
    1.20
    🆕
    1.10
    ean
    1.08
     который
    1.05
     Kości
    1.04
    lana
    1.03
     которая
    1.03
     increíbles
    1.03
    nez
    1.02
    Activations Density 0.019%

    No Known Activations