© 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. 118965
    Prev
    Next
    INDEX
    Explanations

    age as field or variable

    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
     the
    -2.52
    怎样的
    -1.42
    が存在
    -1.40
     our
    -1.38
    éma
    -1.36
    し
    -1.34
     REPRESENTATIVES
    -1.34
     to
    -1.34
     consideran
    -1.33
     why
    -1.30
    POSITIVE LOGITS
     was
    2.03
     كبيرة
    1.59
    巒
    1.48
     جميلة
    1.48
    öhne
    1.41
    ’
    1.41
    )
    1.37
     árabe
    1.37
     الآن
    1.34
    けると
    1.34
    Activations Density 0.015%

    No Known Activations