© 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. 80656
    Prev
    Next
    INDEX
    Explanations

    possession or state of being

    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
     themselves
    -1.70
    figuren
    -1.55
     麵
    -1.49
     informée
    -1.42
     whoſe
    -1.41
    aktivi
    -1.41
    IZONT
    -1.39
    statistik
    -1.39
     resultaten
    -1.38
    ⊝
    -1.38
    POSITIVE LOGITS
     a
    1.71
    this
    1.46
     more
    1.36
    </h1>
    1.33
     other
    1.31
     either
    1.27
    三百
    1.26
    觔
    1.23
    鑑賞
    1.22
    ToListAsync
    1.22
    Activations Density 0.029%

    No Known Activations