© 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. 41906
    Prev
    Next
    INDEX
    Explanations

    Sierra Leone, Sierra Vista

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

    This neuron responds to occurrences of the proper name “Sierra,” especially as part of geographic place names like “Sierra Leone.”

    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
    ѣмъ
    -2.64
    
    -2.45
    塤
    -2.42
     ส์
    -2.36
    isesta
    -2.22
    灃
    -2.22
    櫪
    -2.20
    鄖
    -2.19
    躂
    -2.17
    栒
    -2.16
    POSITIVE LOGITS
    );
    2.50
     continúas
    2.47
    </h1>
    2.47
     \
    2.36
    ),
    2.28
    ("")]
    2.20
    );
    2.20
    \_
    2.19
    ):
    2.17
     '
    2.16
    Activations Density 0.005%

    No Known Activations