© 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. 10-GEMMASCOPE-RES-131K
    7. 74518
    Prev
    Next
    INDEX
    Explanations

    Warden

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

    The neuron strongly activates on the term “Warden,” consistently detecting that specific word in legal document headers.

    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
     ältere
    -2.83
    逕
    -2.80
    辚
    -2.69
    
    -2.55
     ehemalige
    -2.53
     proclaim
    -2.52
    室外
    -2.47
    恣
    -2.47
     Não
    -2.42
    
    -2.42
    POSITIVE LOGITS
    t
    2.55
    in
    2.39
    孩子的
    2.36
    1
    2.28
    ()
    2.20
    內的
    2.17
    有一個
    2.16
    ⦊
    2.14
    ><
    2.11
    but
    2.08
    Activations Density 0.011%

    No Known Activations