© 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. 44720
    Prev
    Next
    INDEX
    Explanations

    vertical alignment and orientation

    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
    “
    -1.93
    ↵↵
    -1.86
    в
    -1.84
    「
    -1.82
     recordar
    -1.73
     There
    -1.70
    ússia
    -1.70
    ers
    -1.66
    ну
    -1.65
    {
    -1.62
    POSITIVE LOGITS
    ଃ
    2.48
    
    2.22
    ᯾
    2.20
    ization
    2.05
    𐐀
    2.02
    嵓
    2.02
    鉨
    2.02
    ୌ
    2.00
    ⼗
    1.97
    ೢ
    1.91
    Activations Density 0.010%

    No Known Activations