© 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. 22-GEMMASCOPE-RES-131K
    7. 84022
    Prev
    Next
    INDEX
    Explanations

    fantastic job

    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_22/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
    說的
    -1.02
    每個
    -0.99
     äta
    -0.96
     服装
    -0.95
    Sådan
    -0.94
    驕
    -0.93
    劵
    -0.92
    tonsoft
    -0.91
     wagon
    -0.90
     distinguir
    -0.90
    POSITIVE LOGITS
     bedeutet
    1.15
     BECAUSE
    1.13
    BIÉN
    1.09
     tornou
    1.07
    打算
    1.07
    很快
    1.07
    havi
    1.05
     最終
    1.05
    eroon
    1.05
     they
    1.04
    Activations Density 0.007%

    No Known Activations