© 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. 67562
    Prev
    Next
    INDEX
    Explanations

    new or updated plans and projects

    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
     anunció
    -1.07
    erobic
    -0.96
    nologies
    -0.96
     gordura
    -0.96
     and
    -0.96
     ceny
    -0.93
     vody
    -0.92
     stát
    -0.92
    uckles
    -0.90
     그것
    -0.90
    POSITIVE LOGITS
     will
    2.03
     new
    1.86
    新的
    1.41
     this
    1.27
     neue
    1.18
     neuen
    1.14
     جدید
    1.12
     apsau
    1.11
     новых
    1.10
    поги
    1.09
    Activations Density 0.070%

    No Known Activations