© 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. 34-GEMMASCOPE-RES-131K
    7. 25551
    Prev
    Next
    INDEX
    Explanations

    grid search

    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
     समी
    -0.84
     Surely
    -0.84
    הג
    -0.82
    ächlich
    -0.82
     Creativity
    -0.81
     스톡
    -0.80
     bluish
    -0.80
    Zdroj
    -0.79
     dàng
    -0.78
     grayish
    -0.78
    POSITIVE LOGITS
    ded
    1.72
     Grid
    1.64
     Gri
    1.32
     grid
    1.21
     grids
    1.19
    grid
    1.17
    グリ
    1.13
    Grid
    1.07
     Gris
    1.07
    BagConstraints
    1.06
    Activations Density 0.010%

    No Known Activations