© 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. 119212
    Prev
    Next
    INDEX
    Explanations

    Date creation or updates

    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
    PHONY
    -0.84
    坑
    -0.83
     Madame
    -0.77
    躺在
    -0.76
     overhaul
    -0.75
    žin
    -0.75
     familien
    -0.74
     Dalton
    -0.74
     梦
    -0.73
    すごく
    -0.73
    POSITIVE LOGITS
     Date
    1.21
    Date
    1.02
     User
    0.99
     DATE
    0.95
     user
    0.90
    user
    0.89
     PhpStorm
    0.87
    DATE
    0.87
     Dokumente
    0.84
    etor
    0.82
    Activations Density 0.037%

    No Known Activations