© 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. 77078
    Prev
    Next
    INDEX
    Explanations

    words starting with que

    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
    ☙
    -0.78
     ихъ
    -0.75
    <bos>
    -0.73
    arı
    -0.72
     питание
    -0.71
    egy
    -0.70
     sentinel
    -0.70
     wszel
    -0.68
    那种
    -0.68
     specifics
    -0.67
    POSITIVE LOGITS
     Queue
    0.93
     QUE
    0.89
     Que
    0.87
    que
    0.85
    Que
    0.84
     quench
    0.83
     quer
    0.82
    quer
    0.82
    qués
    0.81
     գ
    0.79
    Activations Density 0.009%

    No Known Activations