© 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. 34-GEMMASCOPE-RES-131K
    7. 63872
    Prev
    Next
    INDEX
    Explanations

    built-in wardrobes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    osg
    -0.78
    pdata
    -0.77
    ::::::::::::::::
    -0.72
    pulsar
    -0.71
     徐
    -0.71
    anges
    -0.69
     XG
    -0.68
    salle
    -0.68
     Mehl
    -0.67
    Blaze
    -0.67
    POSITIVE LOGITS
     built
    1.69
     wardrobes
    1.65
    Built
    1.57
     wardrobe
    1.57
    built
    1.55
     Built
    1.52
     robes
    1.18
     Wardrobe
    1.16
     Ward
    1.15
    Ward
    1.10
    Activations Density 0.011%

    No Known Activations