© 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. 34-GEMMASCOPE-RES-131K
    7. 32365
    Prev
    Next
    INDEX
    Explanations

    New Year celebrating

    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
    summer
    -0.91
    Easter
    -0.90
     summer
    -0.86
    irma
    -0.79
    weł
    -0.79
    oland
    -0.78
     Cannes
    -0.75
     frequency
    -0.75
    Summer
    -0.75
    清明
    -0.75
    POSITIVE LOGITS
     usher
    1.74
     resolutions
    1.61
     ringing
    1.59
     New
    1.46
     countdown
    1.44
     réve
    1.40
     fireworks
    1.35
     midnight
    1.35
    新年
    1.33
     Resolutions
    1.31
    Activations Density 0.035%

    No Known Activations