© 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. 32444
    Prev
    Next
    INDEX
    Explanations

    edges and graph structures

    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
     кръ
    -0.85
    ̓
    -0.78
    cocci
    -0.72
    丸
    -0.71
    LookAnd
    -0.69
    webkit
    -0.68
    vaders
    -0.67
     terceiro
    -0.66
    amazonaws
    -0.66
    positories
    -0.66
    POSITIVE LOGITS
     edges
    3.08
     edge
    2.95
    edge
    2.33
     Edge
    2.25
    edges
    2.23
    Edges
    2.22
     Edges
    2.17
    Edge
    2.16
     EDGE
    2.03
    EDGE
    1.77
    Activations Density 0.042%

    No Known Activations