© 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. 103226
    Prev
    Next
    INDEX
    Explanations

    Jack followed by names/words

    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
    fuls
    -0.88
     these
    -0.83
    私たちは
    -0.79
     domestique
    -0.79
    Достоинства
    -0.79
    st
    -0.78
     adik
    -0.75
    mates
    -0.74
     anden
    -0.73
    NERS
    -0.72
    POSITIVE LOGITS
    Jack
    1.57
     Jack
    1.52
    Rabbit
    1.25
    rabbit
    1.25
    jack
    1.21
     jack
    1.19
    queline
    1.19
    knife
    1.16
    daw
    1.05
    JACK
    1.05
    Activations Density 0.011%

    No Known Activations