© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67266
    Prev
    Next
    INDEX
    Explanations

    downloading from internet and web APIs

    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
     familiale
    -1.16
    Scénario
    -1.12
     созда
    -1.11
     создание
    -1.05
     dopo
    -1.02
    CREATED
    -1.00
    Leben
    -1.00
     família
    -0.98
     publicação
    -0.96
     feria
    -0.96
    POSITIVE LOGITS
     websites
    1.10
    External
    1.05
     internet
    1.05
     urllib
    1.02
     external
    1.02
     sources
    1.01
     online
    1.00
     via
    0.97
     overseas
    0.97
     Internet
    0.93
    Activations Density 0.128%

    No Known Activations