© 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. 72937
    Prev
    Next
    INDEX
    Explanations

    check out

    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
    According
    -1.49
     even
    -1.30
     actually
    -1.29
    ových
    -1.29
    Starring
    -1.27
     always
    -1.25
     -
    -1.22
     never
    -1.21
    aturi
    -1.20
     verdade
    -1.16
    POSITIVE LOGITS
    ——”
    1.54
    ubernur
    1.50
    켄
    1.39
     другая
    1.38
     nifer
    1.36
    עים
    1.33
     ostavi
    1.32
    旨在
    1.31
    었습니다
    1.30
    ৳
    1.29
    Activations Density 0.220%

    No Known Activations