© 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. 34-GEMMASCOPE-RES-131K
    7. 75454
    Prev
    Next
    INDEX
    Explanations

    speaker or audio devices

    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_34/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
    </b>
    -1.34
    方法
    -0.93
    加
    -0.93
     работы
    -0.91
     almacen
    -0.91
    ノ
    -0.91
    ↵
    -0.90
    ametro
    -0.89
     regard
    -0.88
    chê
    -0.88
    POSITIVE LOGITS
     님
    1.14
    phone
    1.13
     bureau
    1.13
    kemeja
    1.13
    鬭
    1.09
    кроссовки
    1.09
     umana
    1.08
     gemeenten
    1.08
    
    1.04
     kinderen
    1.02
    Activations Density 0.008%

    No Known Activations