© 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. 130583
    Prev
    Next
    INDEX
    Explanations

    descriptive qualities or states

    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
     Redewendung
    -1.02
     which
    -1.02
     crisi
    -0.99
     творо
    -0.99
    ecé
    -0.97
     Bewußt
    -0.94
    CARACTERÍSTICAS
    -0.94
     esportivo
    -0.93
     that
    -0.92
     pudesse
    -0.92
    POSITIVE LOGITS
     và
    1.04
    すっ
    1.03
     และ
    1.00
    死ぬ
    1.00
    用于
    0.93
    ⚢
    0.93
     distintos
    0.93
     этой
    0.91
     یا
    0.90
    昔の
    0.89
    Activations Density 0.028%

    No Known Activations