© 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. 22-GEMMASCOPE-RES-131K
    7. 34936
    Prev
    Next
    INDEX
    Explanations

    you and your

    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_22/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
     vru
    -1.53
     applau
    -1.53
     actuellement
    -1.41
     perpé
    -1.37
     faciliter
    -1.37
     maxime
    -1.35
     cursus
    -1.35
     voler
    -1.32
     meras
    -1.32
     pompe
    -1.32
    POSITIVE LOGITS
     your
    5.03
     you
    4.75
     You
    2.22
    You
    2.20
    你的
    2.00
     if
    1.99
     yourself
    1.98
    あなたが
    1.98
    Your
    1.96
    your
    1.95
    Activations Density 0.020%

    No Known Activations