© 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. 34921
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation

    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
     again
    -1.17
     another
    -1.04
     yine
    -0.99
     zase
    -0.93
     ebenfalls
    -0.92
    again
    -0.91
     nuevamente
    -0.90
     intptr
    -0.89
    Another
    -0.88
     cuando
    -0.88
    POSITIVE LOGITS
     read
    3.28
     Read
    2.45
    Read
    2.17
     continue
    2.16
     Continue
    2.13
    continue
    2.09
    read
    2.02
     let
    1.95
     keep
    1.95
     below
    1.87
    Activations Density 0.110%

    No Known Activations