© 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. 54006
    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
     garagem
    -1.05
     habló
    -1.05
    autogui
    -1.02
    *}[
    -0.98
    によく
    -0.97
     wydar
    -0.96
    いかがでしたか
    -0.96
    invention
    -0.96
    の高い
    -0.95
    marcos
    -0.95
    POSITIVE LOGITS
    ^{\
    1.11
     même
    1.05
     BitSet
    0.99
    ük
    0.97
    нах
    0.96
     дешевле
    0.95
     tổng
    0.94
    酗
    0.94
    च
    0.94
     crane
    0.94
    Activations Density 0.000%

    No Known Activations