© 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. 68705
    Prev
    Next
    INDEX
    Explanations

    again

    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
    了一眼
    -1.04
     for
    -1.03
     queijo
    -1.00
    一般
    -0.98
     inom
    -0.96
     and
    -0.95
     ۰
    -0.94
    iecie
    -0.94
    وى
    -0.94
    通常
    -0.94
    POSITIVE LOGITS
     again
    1.83
     다시
    1.60
     novamente
    1.45
     ponownie
    1.45
    again
    1.40
     nuevamente
    1.26
    nowu
    1.26
     nochmals
    1.25
    再び
    1.23
     nuovamente
    1.23
    Activations Density 0.035%

    No Known Activations