© 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. 10-GEMMASCOPE-RES-131K
    7. 41241
    Prev
    Next
    INDEX
    Explanations

    hinges, box, bread, python, fluid, cream, paper, chocolate, guns, styrofoam

    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
    ،
    -1.30
     our
    -1.28
    Цитата
    -1.26
    zydent
    -1.26
     at
    -1.24
    greenrobot
    -1.24
     ۰
    -1.23
     improved
    -1.20
    ogues
    -1.20
     atriz
    -1.19
    POSITIVE LOGITS
     další
    1.45
    もありますが
    1.41
     Enough
    1.38
     tiež
    1.34
    berapa
    1.27
    greg
    1.26
     svůj
    1.26
    に行って
    1.23
     genoeg
    1.22
     lastly
    1.21
    Activations Density 0.071%

    No Known Activations