© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56846
    Prev
    Next
    INDEX
    Explanations

    types of bags

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     liquid
    -0.78
    alal
    -0.77
    killer
    -0.74
     Athe
    -0.69
     shoes
    -0.69
     schoenen
    -0.68
    覚えて
    -0.68
     спросил
    -0.67
     éti
    -0.66
     cleats
    -0.65
    POSITIVE LOGITS
     crossbody
    1.21
     pouch
    1.13
     shoulder
    1.05
     Messenger
    1.02
     Shoulder
    1.01
     messenger
    0.98
     waist
    0.98
     Pouch
    0.94
     کوچک
    0.94
     organizer
    0.93
    Activations Density 0.019%

    No Known Activations