© 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. 66321
    Prev
    Next
    INDEX
    Explanations

    Finn and Ferdinand names

    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
    </h4>
    -3.27
     oluşan
    -2.97
    ↵
    -2.77
     impetus
    -2.70
    并没有
    -2.64
     efforts
    -2.63
     tomando
    -2.59
     antics
    -2.55
     -"
    -2.55
    ...."
    -2.52
    POSITIVE LOGITS
    I
    3.06
    \
    3.02
    {
    2.84
     函数
    2.52
    訝
    2.39
     From
    2.34
     prata
    2.30
     If
    2.28
    鹛
    2.27
    嗚
    2.25
    Activations Density 0.005%

    No Known Activations