© 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. 70381
    Prev
    Next
    INDEX
    Explanations

    new items

    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
    えっ
    -1.31
     после
    -1.31
     させ
    -1.21
    珦
    -1.20
    ほら
    -1.19
    ようになって
    -1.18
    ごめん
    -1.17
     OGSÅ
    -1.16
     znajdu
    -1.15
    цена
    -1.14
    POSITIVE LOGITS
     corpi
    1.31
     augusti
    1.30
     merce
    1.27
     sadar
    1.24
     otel
    1.23
     fald
    1.23
     calda
    1.23
     feltro
    1.22
     alip
    1.21
     valde
    1.21
    Activations Density 0.028%

    No Known Activations