© 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. 102129
    Prev
    Next
    INDEX
    Explanations

    single digits, double header, sport utility

    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
     étan
    -1.93
    笮
    -1.66
     Teraz
    -1.66
     Then
    -1.60
     Jeśli
    -1.58
    俢
    -1.57
    Nazwa
    -1.56
     飯店
    -1.56
    sukienka
    -1.54
     our
    -1.52
    POSITIVE LOGITS
    了一口
    1.88
    几分
    1.60
    出了一
    1.59
    =
    1.55
     averages
    1.48
    的黑
    1.45
     categor
    1.42
    geoning
    1.40
     zondag
    1.39
     indruk
    1.38
    Activations Density 0.149%

    No Known Activations