© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85407
    Prev
    Next
    INDEX
    Explanations

    Australian followed by an entity

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

    The neuron primarily detects the word “Australian” (and close mentions of Australia).

    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
    螄
    -3.13
     The
    -3.06
     
    -3.05
    他的
    -2.81
     Для
    -2.69
    樒
    -2.64
    赑
    -2.53
     Когда
    -2.47
    鵟
    -2.42
     Untuk
    -2.36
    POSITIVE LOGITS
    The
    3.20
    姈
    2.81
    呖
    2.78
    怍
    2.73
    馘
    2.72
     "";
    2.63
    柵
    2.59
    酲
    2.58
    鯓
    2.47
    厠
    2.42
    Activations Density 0.016%

    No Known Activations