© 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. 98191
    Prev
    Next
    INDEX
    Explanations

    jugular

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "jug" and its variations like "jugular", "juggernaut", and "jugal".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     EMA
    -0.77
     Moments
    -0.75
     Months
    -0.73
     detri
    -0.73
    фай
    -0.72
    addLast
    -0.72
     Moderate
    -0.71
    FontWeight
    -0.71
    versies
    -0.71
    譲
    -0.70
    POSITIVE LOGITS
    Jug
    1.14
     jug
    1.13
     Jug
    1.10
    jug
    1.03
     juggling
    0.94
    psychological
    0.85
    gling
    0.84
     jugs
    0.83
    gernaut
    0.80
     camadas
    0.79
    Activations Density 0.015%

    No Known Activations