© 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. 34-GEMMASCOPE-RES-131K
    7. 93829
    Prev
    Next
    INDEX
    Explanations

    evaluation and analysis processes

    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_34/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
    étranger
    -1.03
    Зно
    -0.91
    是没有
    -0.90
     zwierząt
    -0.90
    צב
    -0.88
    组合
    -0.88
     preparazione
    -0.88
     amerikanischen
    -0.88
     отметил
    -0.87
     Nachfolger
    -0.87
    POSITIVE LOGITS
     of
    2.52
     tools
    1.44
     and
    1.36
     exercise
    1.32
     tool
    1.32
    tool
    1.23
     procedure
    1.09
     process
    1.09
    Tool
    1.08
     for
    1.07
    Activations Density 0.131%

    No Known Activations