© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90767
    Prev
    Next
    INDEX
    Explanations

    JSON structure parsing

    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
    UKAN
    -0.76
    jí
    -0.71
    yuk
    -0.71
     fotografía
    -0.70
    TUR
    -0.70
    同志
    -0.69
    Cosmos
    -0.69
     homogen
    -0.68
    plank
    -0.68
    ям
    -0.67
    POSITIVE LOGITS
     nostalgia
    0.68
     Std
    0.63
    fmt
    0.63
    seling
    0.62
     verksamhet
    0.61
     registr
    0.61
     fores
    0.60
    LoadBalancer
    0.60
     cox
    0.60
    룻
    0.60
    Activations Density 0.060%

    No Known Activations