© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 131034
    Prev
    Next
    INDEX
    Explanations

    leisure activities and free time hobbies

    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_22/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
     уже
    -1.25
     already
    -1.16
     вже
    -1.09
    ógica
    -1.04
     неприят
    -1.02
     bereits
    -1.01
     allerede
    -1.00
     już
    -1.00
     Wartawan
    -0.99
     the
    -0.98
    POSITIVE LOGITS
     hobbies
    1.22
    Being
    1.13
    Which
    1.13
    我喜欢
    1.11
    Outside
    1.10
    classNames
    1.05
    Enjoy
    1.03
    larda
    1.01
    Absolutely
    0.99
    ceased
    0.98
    Activations Density 0.012%

    No Known Activations