© 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. 130519
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on occurrences of the token “West,” especially when it appears in proper names or geographic references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    West followed by specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    <bos>
    -2.84
    儅
    -2.70
    '
    -2.55
     
    -2.48
    籥
    -2.47
    打开了
    -2.42
    書いて
    -2.22
     disregarding
    -2.20
    馓
    -2.17
    スム
    -2.16
    POSITIVE LOGITS
    );
    2.50
    s
    2.44
    iembre
    2.36
    。《
    2.36
     In
    2.36
    一些
    2.31
    я
    2.27
     truest
    2.25
    </sup>
    2.23
     Because
    2.23
    Activations Density 0.027%

    No Known Activations