© 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. 108865
    Prev
    Next
    INDEX
    Explanations

    death and departure

    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
    忙碌
    -0.73
     الصيف
    -0.72
    巻き
    -0.71
    灵活
    -0.71
    ann
    -0.71
     mód
    -0.70
     增
    -0.70
    )=>{
    -0.70
    RTLU
    -0.69
    轢
    -0.69
    POSITIVE LOGITS
     transition
    1.85
     departure
    1.73
     Transition
    1.56
     depart
    1.55
    transition
    1.46
     departing
    1.45
     transitioning
    1.44
     departed
    1.42
     transitions
    1.38
     transitioned
    1.36
    Activations Density 0.011%

    No Known Activations