© 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. 71301
    Prev
    Next
    INDEX
    Explanations

    code snippets from programming languages

    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
    IsString
    -0.96
    keiten
    -0.93
    olite
    -0.92
    翃
    -0.90
    matisch
    -0.89
     entstehen
    -0.88
    already
    -0.88
    Already
    -0.86
    amientos
    -0.85
    ково
    -0.85
    POSITIVE LOGITS
     will
    1.11
     had
    0.94
     statunitense
    0.91
     Remember
    0.89
     veldig
    0.87
     pousada
    0.86
     Exe
    0.86
     они
    0.86
    Kval
    0.86
    dued
    0.85
    Activations Density 0.002%

    No Known Activations