© 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. 58533
    Prev
    Next
    INDEX
    Explanations

    enjoyment and liking

    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
    ubehör
    -0.98
     strtolower
    -0.89
    торой
    -0.78
    式
    -0.77
    ()),
    -0.75
     on
    -0.75
    小孩
    -0.74
     item
    -0.74
    ningarna
    -0.74
    EQUALS
    -0.74
    POSITIVE LOGITS
     enjoy
    4.75
     Enjoy
    4.47
    Enjoy
    4.47
    enjoy
    3.73
     ENJOY
    3.31
     enjoys
    2.97
     enjoying
    2.84
     enjoyment
    2.81
     enjoyed
    2.73
    ENJOY
    2.73
    Activations Density 0.104%

    No Known Activations