© 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. 34-GEMMASCOPE-RES-131K
    7. 87127
    Prev
    Next
    INDEX
    Explanations

    certificate trust anchors

    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_34/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
    ട
    -0.86
    koop
    -0.78
    lägen
    -0.75
    　　[
    -0.75
    itarios
    -0.71
    Adaptive
    -0.70
    ыгана
    -0.70
    ってくる
    -0.69
     adaptive
    -0.68
    Gentlemen
    -0.66
    POSITIVE LOGITS
     CA
    1.41
     trust
    1.31
     Root
    1.25
     root
    1.23
     trusted
    1.22
     Trust
    1.21
    Trust
    1.21
    Root
    1.18
    CA
    1.14
    trust
    1.14
    Activations Density 0.064%

    No Known Activations