© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49093
    Prev
    Next
    INDEX
    Explanations

    physical memory mapping

    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
    elancer
    -0.73
    awsze
    -0.70
     Corporation
    -0.69
     Kry
    -0.69
     Eternal
    -0.69
    tactical
    -0.69
     Protección
    -0.69
     Copy
    -0.68
     Directed
    -0.68
     Raum
    -0.68
    POSITIVE LOGITS
    BUG
    0.86
    GetObject
    0.81
    virt
    0.78
    olkien
    0.78
    SATA
    0.77
    WARN
    0.76
     fisico
    0.75
     octane
    0.75
    haw
    0.72
    Dé
    0.72
    Activations Density 0.031%

    No Known Activations