© 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. 10-GEMMASCOPE-RES-131K
    7. 61140
    Prev
    Next
    INDEX
    Explanations

    ambassador or advocate

    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_10/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
     not
    -1.89
     After
    -1.46
    ↵
    -1.41
     In
    -1.40
    .
    -1.37
     =
    -1.31
    sonaro
    -1.30
     all
    -1.28
     Going
    -1.28
    ."
    -1.27
    POSITIVE LOGITS
    ⦊
    1.63
     pérd
    1.58
     garant
    1.48
     tada
    1.47
    {`
    1.45
     elim
    1.44
     publie
    1.40
    獁
    1.40
    ſchen
    1.38
     daug
    1.38
    Activations Density 0.050%

    No Known Activations