© 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. 117987
    Prev
    Next
    INDEX
    Explanations

    geometric operations and data types

    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
     layer
    -0.83
    łem
    -0.74
     layers
    -0.74
    alling
    -0.73
     слоя
    -0.73
    Excel
    -0.73
    人力
    -0.73
    Layer
    -0.72
     centralised
    -0.72
    ര
    -0.71
    POSITIVE LOGITS
     Multi
    1.13
     rings
    1.03
    Multi
    0.99
     GE
    0.98
     Ring
    0.98
    exterior
    0.98
     multi
    0.93
     EMPTY
    0.93
     geometries
    0.93
     MULTI
    0.93
    Activations Density 0.031%

    No Known Activations