© 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. 76037
    Prev
    Next
    INDEX
    Explanations

    names after manager

    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
    にならない
    -0.79
     WeChat
    -0.75
     monet
    -0.73
    GRID
    -0.71
     selfie
    -0.70
     khoản
    -0.69
     mone
    -0.68
     Humberto
    -0.67
     Hazel
    -0.66
     Raspberry
    -0.66
    POSITIVE LOGITS
    ιά
    0.85
     millennium
    0.82
     Kosovo
    0.81
    itech
    0.79
    ണ്ട
    0.79
     UIImage
    0.75
     Millennium
    0.75
     mille
    0.75
    mill
    0.74
    तः
    0.73
    Activations Density 0.111%

    No Known Activations