© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85715
    Prev
    Next
    INDEX
    Explanations

    emerged as a role or status

    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
     to
    -2.06
     that
    -2.00
    𐐪
    -1.90
    นั้น
    -1.55
    朏
    -1.53
     الاجتماعي
    -1.52
    几个月
    -1.52
    >−
    -1.49
    úgó
    -1.46
    безпе
    -1.45
    POSITIVE LOGITS
     also
    1.74
     only
    1.63
     vinos
    1.63
    をご覧ください
    1.58
    のご紹介
    1.56
    着一个
    1.55
     participado
    1.52
    ції
    1.45
    sukienka
    1.45
    栻
    1.45
    Activations Density 0.041%

    No Known Activations