© 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. 84440
    Prev
    Next
    INDEX
    Explanations

    Q: questions and titles

    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
     Alain
    -0.78
    🧺
    -0.76
     oriente
    -0.75
     insensible
    -0.75
    liny
    -0.75
     Napoléon
    -0.73
    kologi
    -0.72
    Gu
    -0.72
     Baron
    -0.72
    letti
    -0.72
    POSITIVE LOGITS
     adoro
    0.79
     ایم
    0.76
    currentNode
    0.75
     suit
    0.73
     CONDUCT
    0.73
     Conduct
    0.73
     cotone
    0.71
     giardino
    0.71
     cutter
    0.70
     مین
    0.69
    Activations Density 0.008%

    No Known Activations