© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57518
    Prev
    Next
    INDEX
    Explanations

    legal services

    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
    formal
    -1.93
     informal
    -1.86
    Formal
    -1.79
     formal
    -1.75
     Formal
    -1.67
     Informal
    -1.60
    Informal
    -1.47
     informally
    -1.19
     formality
    -1.17
     formalized
    -1.16
    POSITIVE LOGITS
     Head
    1.27
     head
    1.05
    Head
    1.05
    HEAP
    0.87
     poverty
    0.77
    HEAD
    0.76
     Migrant
    0.76
     HEAD
    0.74
     μυ
    0.72
     Outlet
    0.71
    Activations Density 0.012%

    No Known Activations