© 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. 74930
    Prev
    Next
    INDEX
    Explanations

    multilingual content context

    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
     if
    -2.11
     there
    -1.95
    噚
    -1.76
    after
    -1.65
    什么呢
    -1.61
     different
    -1.58
    せよ
    -1.55
    ætter
    -1.55
     at
    -1.53
    高校生
    -1.52
    POSITIVE LOGITS
     två
    1.56
     of
    1.55
     dergleichen
    1.52
    owanie
    1.48
    s
    1.48
     zei
    1.47
     tehd
    1.45
     degrés
    1.44
     étages
    1.44
     dictionnaire
    1.43
    Activations Density 0.057%

    No Known Activations