© 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. 10-GEMMASCOPE-RES-131K
    7. 42992
    Prev
    Next
    INDEX
    Explanations

    high performance, resolution, school

    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_10/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
      
    -3.83
     “
    -3.67
          
    -3.34
    <
    -2.98
    >
    -2.91
    *
    -2.67
    ']>
    -2.61
     I
    -2.61
    {
    -2.61
    (
    -2.59
    POSITIVE LOGITS
    禇
    3.27
    s
    3.08
     ambientale
    2.84
    ୌ
    2.84
    メリカ
    2.84
     příjem
    2.78
     errori
    2.78
    kunjung
    2.77
     obiettivi
    2.70
     menatap
    2.70
    Activations Density 0.081%

    No Known Activations