© 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. 129778
    Prev
    Next
    INDEX
    Explanations

    to help, provide, create, manage, develop

    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
     after
    -1.72
     when
    -1.64
     any
    -1.57
     during
    -1.57
     but
    -1.52
     querían
    -1.52
    儼
    -1.48
     had
    -1.45
    するに
    -1.45
    Surprisingly
    -1.45
    POSITIVE LOGITS
     лучше
    1.43
    1.42
     bridge
    1.38
    dani
    1.37
     Bewertungen
    1.35
     !!!!
    1.34
     tạo
    1.34
    的是
    1.34
    龊
    1.31
     architect
    1.30
    Activations Density 0.112%
    No Known Activations