© 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. 104385
    Prev
    Next
    INDEX
    Explanations

    services and multilingual terms

    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
     quite
    -1.16
     this
    -1.09
    .」
    -1.09
     when
    -1.05
     it
    -1.05
    ariamente
    -1.02
     where
    -0.99
     hoping
    -0.99
     blatantly
    -0.99
     toneladas
    -0.97
    POSITIVE LOGITS
    所有人都
    1.20
    还是很
    1.05
     السياس
    0.97
     字体
    0.96
    Anyone
    0.96
     castig
    0.94
    甭
    0.94
    嘚
    0.94
    色んな
    0.93
    önes
    0.93
    Activations Density 0.002%

    No Known Activations