© 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. 9391
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     who
    -1.33
     their
    -1.17
     whose
    -1.06
     言
    -1.02
    jointe
    -0.98
     all
    -0.97
     sexto
    -0.96
     when
    -0.95
    \#:
    -0.95
    DialogInterface
    -0.94
    POSITIVE LOGITS
     tumbuhan
    1.30
    Capítulo
    1.14
    选择
    1.12
     produrre
    1.05
     关闭
    1.05
    Asie
    1.05
     OnDestroy
    1.02
    結果
    1.02
    Jika
    1.02
     seguenti
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.