© 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. 25622
    Prev
    Next
    INDEX
    Explanations

    imports and computer programming

    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
     that
    -1.48
     during
    -1.32
     with
    -1.23
     when
    -1.16
     while
    -1.13
     without
    -1.09
     taking
    -1.05
     numerous
    -1.05
     immediately
    -1.02
     whenever
    -1.02
    POSITIVE LOGITS
     JPanel
    0.99
     ered
    0.93
    日を
    0.91
    ætte
    0.89
     augus
    0.88
     کیلوم
    0.88
    oneg
    0.87
     ВО
    0.86
     audit
    0.85
     этаж
    0.85
    Activations Density 0.027%

    No Known Activations