© 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. 73464
    Prev
    Next
    INDEX
    Explanations

    lightweight shelter

    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
    oplayer
    -0.85
    𝒔
    -0.85
    pulumi
    -0.84
    Πηγές
    -0.79
    makedirs
    -0.77
    tadiene
    -0.77
    斛
    -0.76
    CRETE
    -0.75
     Prak
    -0.75
     Staub
    -0.74
    POSITIVE LOGITS
     ul
    1.43
     lightest
    1.21
     shelter
    1.05
     Ul
    1.02
    shelter
    0.98
    Ul
    0.96
     minimalist
    0.95
     lightweight
    0.94
     compres
    0.94
    Lightweight
    0.94
    Activations Density 0.020%

    No Known Activations