© 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. 44388
    Prev
    Next
    INDEX
    Explanations

    contralateral or ipsilateral body parts

    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
     andere
    -1.50
     gustaMe
    -1.45
    hålla
    -1.38
    壅
    -1.35
     echte
    -1.34
     vanske
    -1.30
     Nebenwirkungen
    -1.27
     saját
    -1.26
     あります
    -1.26
     улице
    -1.26
    POSITIVE LOGITS
    當中
    1.42
     possesses
    1.39
     &&
    1.38
     ufficiali
    1.30
     pubblici
    1.28
     Portugu
    1.26
     riguarda
    1.25
    可以说
    1.24
    ():
    1.23
    ganu
    1.22
    Activations Density 0.007%

    No Known Activations