© 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. 42532
    Prev
    Next
    INDEX
    Explanations

    voice assistants

    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_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
    吖
    -3.41
    नलोड
    -3.20
    沨
    -2.64
    呓
    -2.61
     Verpflich
    -2.61
     Eigentümer
    -2.50
    
    -2.48
     feiner
    -2.47
     said
    -2.45
    ～～
    -2.42
    POSITIVE LOGITS
    ра
    2.50
    ra
    2.48
    ка
    2.44
    is
    2.42
    ti
    2.33
    B
    2.33
    时
    2.23
    )
    2.19
    時に
    2.14
    不可思议
    2.13
    Activations Density 0.004%

    No Known Activations