© 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. 38795
    Prev
    Next
    INDEX
    Explanations

    Puerto Rico

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

    The neuron activates on place names and geographic references to Puerto Rico (e.g., “Puerto Rico,” “San Juan,” local venues, Hurricane Maria).

    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
    -2.83
    5
    -2.67
    9
    -2.66
    7
    -2.53
    6
    -2.42
    \
    -2.41
    3
    -2.34
    4
    -2.28
    8
    -2.06
    ...
    -1.99
    POSITIVE LOGITS
     magnética
    1.98
    vantaged
    1.90
     Flughafen
    1.84
     INFORMACIÓN
    1.81
    нью
    1.78
    齟
    1.77
    ficulties
    1.74
     famí
    1.72
     asisti
    1.72
    鱂
    1.71
    Activations Density 0.006%

    No Known Activations