© 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. 22-GEMMASCOPE-RES-131K
    7. 67823
    Prev
    Next
    INDEX
    Explanations

    quantities and units conversion

    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_22/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
     Semoga
    -1.15
     comida
    -1.13
     componentes
    -1.09
    ֝
    -1.09
     Apakah
    -1.07
    iramente
    -1.07
    してる
    -1.06
     Pilih
    -1.05
     recomand
    -1.02
     Lainnya
    -1.02
    POSITIVE LOGITS
     quantités
    1.27
     hvilken
    1.20
     who
    1.18
     ayude
    1.17
    +/**
    1.12
     kroppen
    1.09
    有多少
    1.08
     stoichio
    1.07
     unités
    1.05
    oproject
    1.05
    Activations Density 0.003%

    No Known Activations