© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130122
    Prev
    Next
    INDEX
    Explanations

    connectives and sentence openers

    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
    ⼿
    -1.41
    corer
    -1.32
     koncentr
    -1.20
    ;;)
    -1.19
    vented
    -1.18
    💚
    -1.18
    TestBed
    -1.16
     hongos
    -1.15
     угло
    -1.15
     зар
    -1.14
    POSITIVE LOGITS
    ，
    1.52
    𝑞
    1.49
    「
    1.36
     '@/
    1.31
     "@/
    1.29
    （
    1.26
    🪛
    1.23
     após
    1.22
     nochmal
    1.21
     después
    1.20
    Activations Density 1.253%

    No Known Activations