© 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. 10-GEMMASCOPE-RES-131K
    7. 123495
    Prev
    Next
    INDEX
    Explanations

    Addressing groups of people

    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_10/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
     both
    -1.70
     each
    -1.16
     mismas
    -1.09
    шного
    -1.06
    ابة
    -1.05
     there
    -1.05
     two
    -1.05
    蜒
    -1.05
     the
    -1.03
     at
    -1.03
    POSITIVE LOGITS
     számára
    1.50
    eachtet
    1.32
     čia
    1.31
     május
    1.30
    隳
    1.29
     június
    1.23
     obyvateľov
    1.18
     Nieuws
    1.18
    ühungen
    1.17
    岽
    1.17
    Activations Density 0.097%

    No Known Activations