© 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. 22-GEMMASCOPE-RES-131K
    7. 14055
    Prev
    Next
    INDEX
    Explanations

    Madagascar and Los Angeles

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

    The neuron flags occurrences of “Madagascar” or related Malagasy names and terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    🔫
    -1.06
     gole
    -1.02
     Química
    -1.00
     Rect
    -0.99
     kuu
    -0.99
    Cô
    -0.98
    priest
    -0.98
    ภาษา
    -0.97
     ingat
    -0.97
     Canadá
    -0.96
    POSITIVE LOGITS
     sensaciones
    1.12
     aislados
    1.10
     manifestaciones
    1.02
    ani
    1.02
    AN
    1.01
     reciben
    1.00
     verdaderas
    1.00
    ヵ
    0.96
     desconocido
    0.95
     lesser
    0.94
    Activations Density 0.003%

    No Known Activations