© 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. 98511
    Prev
    Next
    INDEX
    Explanations

    table of contents descriptions

    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
    Aç
    -1.15
     sembla
    -1.12
    According
    -1.03
     activité
    -1.02
     作り方
    -1.02
     ИЗ
    -1.02
     profondeur
    -0.96
    hese
    -0.95
    Koordin
    -0.95
    ători
    -0.95
    POSITIVE LOGITS
     how
    1.82
     overview
    1.58
     why
    1.54
     about
    1.37
     then
    1.19
     summary
    1.19
     Overview
    1.16
     description
    1.15
     questions
    1.12
     followed
    1.12
    Activations Density 0.048%

    No Known Activations