© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99855
    Prev
    Next
    INDEX
    Explanations

    date ranges

    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
    uransi
    -0.93
     gått
    -0.93
     الشهر
    -0.91
    booted
    -0.91
    lllllll
    -0.91
     после
    -0.90
     starts
    -0.90
    ерез
    -0.90
    rages
    -0.89
    winston
    -0.88
    POSITIVE LOGITS
     latest
    1.94
    latest
    1.73
    Latest
    1.34
    最新的
    1.34
    最新
    1.25
     last
    1.23
     最新
    1.20
     Latest
    1.16
     recent
    1.11
     newest
    1.04
    Activations Density 0.059%

    No Known Activations