© 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. 6886
    Prev
    Next
    INDEX
    Explanations

    of the license version

    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
     which
    -1.85
     five
    -1.66
     two
    -1.63
     possibly
    -1.62
     three
    -1.59
     their
    -1.57
     ostensibly
    -1.56
     relatively
    -1.55
     partially
    -1.55
     at
    -1.54
    POSITIVE LOGITS
     interrom
    1.52
    镲
    1.49
     🥰
    1.48
     wondrous
    1.45
     hahaha
    1.43
    すっ
    1.41
     😊
    1.41
     Dinas
    1.38
     lauded
    1.38
     💕
    1.38
    Activations Density 0.319%

    No Known Activations