© 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. 84960
    Prev
    Next
    INDEX
    Explanations

    Kickstarted, place on, default offering

    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
    viť
    -0.70
    CLC
    -0.70
    标准
    -0.66
     Abor
    -0.66
     Tätigkeit
    -0.66
    長的
    -0.65
     Walkover
    -0.64
     vectra
    -0.63
     Andorra
    -0.63
     porsche
    -0.63
    POSITIVE LOGITS
     faire
    0.73
    什么是
    0.73
     vů
    0.72
     piedras
    0.72
     дописавши
    0.71
     Kish
    0.71
     nek
    0.70
     ברי
    0.70
     kri
    0.68
     Adrian
    0.68
    Activations Density 0.052%

    No Known Activations