© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119396
    Prev
    Next
    INDEX
    Explanations

    manner, condition, or time

    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
     already
    -1.62
     già
    -1.59
    臯
    -1.34
     caracteriza
    -1.32
     colocar
    -1.32
     utilizando
    -1.30
     deten
    -1.27
     didn
    -1.25
     hiperten
    -1.25
     Может
    -1.24
    POSITIVE LOGITS
     by
    4.38
     maupun
    1.69
     because
    1.67
     توسط
    1.65
     oleh
    1.64
     there
    1.63
     estatales
    1.48
    、【
    1.46
    )&
    1.43
     meninggal
    1.38
    Activations Density 2.146%

    No Known Activations