© 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. 102806
    Prev
    Next
    INDEX
    Explanations

    properties and linearity

    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
     analisar
    -0.77
    udes
    -0.75
    academy
    -0.75
    Analysis
    -0.73
    féle
    -0.72
    corrência
    -0.71
     салат
    -0.71
    ⋀
    -0.71
    ်း
    -0.71
    liz
    -0.71
    POSITIVE LOGITS
     properties
    1.51
     linearity
    1.44
     Properties
    1.39
     property
    1.32
    PROPERTIES
    1.24
    Properties
    1.20
     distributes
    1.16
     distributive
    1.16
    properties
    1.16
     обладает
    1.13
    Activations Density 0.043%

    No Known Activations