© 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. 10-GEMMASCOPE-RES-131K
    7. 65292
    Prev
    Next
    INDEX
    Explanations

    Antarctica and Antarctic regions

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

    The neuron is specialized in detecting references to Antarctica or Antarctic-related place names.

    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
    氿
    -2.34
    饪
    -2.23
    えっ
    -2.19
    퐿
    -2.06
    
    -2.06
    lossians
    -2.05
    玙
    -2.03
    
    -1.98
     当前
    -1.89
    􀂃
    -1.88
    POSITIVE LOGITS
    ↵
    3.31
    呖
    2.30
    </h6>
    2.22
    嗖
    2.13
    </sup>
    1.97
    </h4>
    1.95
     игрушка
    1.95
    ⻄
    1.93
    </h3>
    1.92
    e
    1.92
    Activations Density 0.003%

    No Known Activations