© 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. 10-GEMMASCOPE-RES-131K
    7. 84555
    Prev
    Next
    INDEX
    Explanations

    profile

    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
    {
    -3.64
    >
    -3.50
    ↵↵
    -3.33
     we
    -3.02
     crucial
    -2.80
    1
    -2.75
     decidedly
    -2.67
     .
    -2.59
     taką
    -2.47
    "
    -2.47
    POSITIVE LOGITS
     hitta
    3.09
     möjligt
    3.09
    ဴ
    2.97
    ſelves
    2.83
    縷
    2.75
    kwür
    2.72
     ajustar
    2.67
    
    2.64
    軼
    2.63
     silencioso
    2.61
    Activations Density 0.011%

    No Known Activations