© 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. 34-GEMMASCOPE-RES-131K
    7. 64530
    Prev
    Next
    INDEX
    Explanations

    preposition indicating location 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_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
     kasama
    -1.45
     papild
    -1.35
     vienas
    -1.34
     upang
    -1.24
     viena
    -1.21
     sako
    -1.20
     iyon
    -1.20
     noong
    -1.18
     habang
    -1.15
     ngayon
    -1.13
    POSITIVE LOGITS
     at
    8.75
     ở
    2.52
     عند
    2.47
    At
    2.41
     tại
    2.30
     At
    2.27
     @
    2.17
    at
    1.99
    於
    1.66
    于
    1.65
    Activations Density 0.309%

    No Known Activations