© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39466
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
     usuário
    -1.41
    ズキ
    -1.30
    付けた
    -1.27
     gyermek
    -1.25
    掲示
    -1.23
    NOTAS
    -1.23
    ৹
    -1.23
     VERY
    -1.23
    𖥧
    -1.23
     นัก
    -1.20
    POSITIVE LOGITS
    もちろん
    1.39
     также
    1.38
    ！」
    1.35
     =
    1.33
     גם
    1.30
    "
    1.30
     этих
    1.28
     like
    1.27
     what
    1.23
    Those
    1.23
    Activations Density 0.066%

    No Known Activations