© 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. 10-GEMMASCOPE-RES-131K
    7. 70498
    Prev
    Next
    INDEX
    Explanations

    numbers that are part of sequences

    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_10/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
    usually
    -1.93
    in
    -1.85
     ambayo
    -1.77
    OOOOOO
    -1.66
    ense
    -1.59
     betreffende
    -1.59
    typically
    -1.59
     kuhusu
    -1.58
     groote
    -1.58
    ering
    -1.57
    POSITIVE LOGITS
     echar
    1.75
     first
    1.70
     school
    1.55
     an
    1.55
     many
    1.54
     если
    1.51
     сегодня
    1.50
    utusan
    1.50
    衕
    1.48
     alleviate
    1.47
    Activations Density 0.098%

    No Known Activations