© 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. 34-GEMMASCOPE-RES-131K
    4. 56054
    Prev
    Next
    INDEX
    Explanations

    numerical quantities

    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_34/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
     beider
    -1.45
     zarówno
    -1.27
     ambos
    -1.26
     banyak
    -1.25
     a
    -1.23
     birçok
    -1.20
    両
    -1.19
     både
    -1.16
     its
    -1.15
    Both
    -1.14
    POSITIVE LOGITS
     two
    4.16
     one
    3.28
    two
    3.17
     three
    3.17
     none
    2.97
     all
    2.89
     två
    2.86
     zwei
    2.55
    none
    2.55
    three
    2.53
    Activations Density 0.221%

    No Known Activations