© 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. 19221
    Prev
    Next
    INDEX
    Explanations

    HttpResponse

    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
     It
    -2.92
     戰
    -2.86
     notwendig
    -2.69
    聍
    -2.66
     schwierig
    -2.53
    لاقات
    -2.50
     gefährlich
    -2.48
    unjung
    -2.48
     preparada
    -2.47
     tenets
    -2.44
    POSITIVE LOGITS
    i
    2.80
    e
    2.80
    是真的
    2.56
     But
    2.53
    2
    2.50
     Konkur
    2.41
    工作的
    2.39
    鱚
    2.39
    さび
    2.39
    alucía
    2.38
    Activations Density 0.021%

    No Known Activations