© 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. 130766
    Prev
    Next
    INDEX
    Explanations

    located or situated

    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
     kedai
    -1.28
     crucial
    -1.25
     then
    -1.24
    iamo
    -1.23
     Example
    -1.23
    opardy
    -1.20
     echip
    -1.19
     modelleri
    -1.18
    rée
    -1.18
    iology
    -1.18
    POSITIVE LOGITS
     located
    1.66
    ׇ
    1.54
     situated
    1.34
     ویتامین
    1.30
     nestled
    1.30
     النبات
    1.25
     besø
    1.20
    گوشی
    1.16
     if
    1.15
    อร่อย
    1.13
    Activations Density 0.162%

    No Known Activations