© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23646
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    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
     ALL
    -1.52
     all
    -1.34
     as
    -1.34
     EVERY
    -1.34
     so
    -1.32
    https
    -1.30
     by
    -1.29
     that
    -1.26
     Those
    -1.26
    МЕН
    -1.24
    POSITIVE LOGITS
     two
    5.19
     three
    4.72
     två
    3.53
     ثلاثة
    3.48
     four
    3.36
     trzech
    3.09
    three
    3.00
     dwóch
    2.98
     tři
    2.92
     kaksi
    2.88
    Activations Density 0.319%

    No Known Activations