© 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. 92531
    Prev
    Next
    INDEX
    Explanations

    juggling and balancing

    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
     kamu
    -0.80
    ssil
    -0.76
    konstru
    -0.75
     tetanus
    -0.75
     år
    -0.72
    կ
    -0.72
    hipping
    -0.71
    voli
    -0.71
    SearchTree
    -0.71
    िल्म
    -0.70
    POSITIVE LOGITS
     juggling
    4.53
     balancing
    4.13
     jug
    4.13
    jug
    3.94
    Jug
    3.80
     Jug
    3.53
    balancing
    3.48
     Balancing
    3.44
    Balancing
    3.30
     balance
    3.27
    Activations Density 0.084%

    No Known Activations