© 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. 10-GEMMASCOPE-RES-131K
    7. 129209
    Prev
    Next
    INDEX
    Explanations

    Madagascar and UI views

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

    The neuron strongly activates on the exact word “Madagascar.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     είναι
    -3.06
    蕯
    -2.84
     both
    -2.38
    t
    -2.22
    由於
    -2.19
    o
    -2.09
     There
    -2.06
    ៚
    -2.05
     dozen
    -2.03
     lavish
    -2.03
    POSITIVE LOGITS
    ፨
    2.70
     AMAZING
    2.64
     mystical
    2.53
    ⚋
    2.42
     delectable
    2.42
    都不是
    2.41
     dreary
    2.41
    就不是
    2.39
    </h1>
    2.34
    娓
    2.34
    Activations Density 0.003%

    No Known Activations