© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31080
    Prev
    Next
    INDEX
    Explanations

    JavaScript closing delimiters

    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
    veys
    -0.88
    ləş
    -0.85
    根
    -0.82
     kendi
    -0.81
     энергии
    -0.79
     SafeArea
    -0.78
     vecka
    -0.78
     Break
    -0.78
    ">{
    -0.77
    ച്ച
    -0.77
    POSITIVE LOGITS
     return
    1.02
    return
    1.00
     there
    0.90
    setTimeout
    0.84
     $('#
    0.84
     $("#
    0.83
    ToReturn
    0.81
     ADAPT
    0.79
     focused
    0.79
    東大
    0.78
    Activations Density 0.023%

    No Known Activations