© 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. 104595
    Prev
    Next
    INDEX
    Explanations

    ws

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

    The neuron fires whenever it encounters the token “ws,” for example in code identifiers or package names (e.g. javax.ws.rs or ws client/connection variables).

    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
    which
    -3.72
    敺
    -3.06
    ﮩ
    -2.88
    赑
    -2.83
    婓
    -2.80
     lupo
    -2.70
     hunde
    -2.70
    otry
    -2.70
    髕
    -2.70
    '))
    -2.69
    POSITIVE LOGITS
    \
    4.16
    *
    3.55
    -
    3.48
    _
    3.11
    I
    3.00
     crux
    2.91
    <
    2.69
    +
    2.69
    ↵↵
    2.64
    翃
    2.53
    Activations Density 0.004%

    No Known Activations