© 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. 71385
    Prev
    Next
    INDEX
    Explanations

    .po/.mo file extensions

    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
    +
    -1.34
     anbieten
    -1.34
    !
    -1.34
    ,
    -1.29
     +
    -1.23
    M
    -1.21
     people
    -1.20
    ....
    -1.20
    ..
    -1.20
    .
    -1.19
    POSITIVE LOGITS
    kwür
    1.60
     stoff
    1.50
     minimalis
    1.49
     boden
    1.43
     nimmer
    1.38
    ፨
    1.34
    桄
    1.33
     deſt
    1.32
     ledig
    1.31
     kleid
    1.31
    Activations Density 0.011%

    No Known Activations