© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102535
    Prev
    Next
    INDEX
    Explanations

    christmas gifts and unwrapping

    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
    rowave
    -0.88
     ない
    -0.80
     Characteristics
    -0.78
    量
    -0.76
     ContentValues
    -0.75
    迸
    -0.75
     گل
    -0.72
     Celebration
    -0.71
     نگهد
    -0.71
    files
    -0.71
    POSITIVE LOGITS
     stockings
    1.80
     stocking
    1.73
     presents
    1.47
     gifts
    1.38
     unwra
    1.24
     Presents
    1.13
    Santa
    1.07
    Opening
    1.04
     opening
    1.00
     Santa
    1.00
    Activations Density 0.025%

    No Known Activations