© 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. 28528
    Prev
    Next
    INDEX
    Explanations

    domain name infrastructure

    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
     our
    -1.72
     with
    -1.69
     before
    -1.62
     and
    -1.52
     we
    -1.48
     without
    -1.48
     during
    -1.47
     that
    -1.44
     over
    -1.41
     alongside
    -1.34
    POSITIVE LOGITS
     royaume
    1.62
    Миха
    1.45
    姈
    1.42
    OBJETIVO
    1.42
    踌
    1.41
    includes
    1.39
     GETS
    1.38
    
    1.38
     utiliser
    1.36
    alians
    1.36
    Activations Density 0.003%

    No Known Activations