© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38667
    Prev
    Next
    INDEX
    Explanations

    specific items or categories

    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
    xxxxx
    -0.98
     Архивировано
    -0.96
     eerst
    -0.94
     châssis
    -0.94
     "${
    -0.94
    uitton
    -0.94
    şme
    -0.94
    explain
    -0.94
    whence
    -0.93
    アリング
    -0.93
    POSITIVE LOGITS
     definition
    1.25
    륜
    1.16
     logro
    1.13
     also
    1.12
     pourrait
    1.10
     podría
    1.07
    렁
    1.05
     кровать
    1.04
     faço
    1.04
     pourriez
    1.04
    Activations Density 0.109%

    No Known Activations