© 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. 10-GEMMASCOPE-RES-131K
    7. 29068
    Prev
    Next
    INDEX
    Explanations

    bringing along

    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
     gradualmente
    -1.47
     `;
    -1.45
     proveniente
    -1.42
     segi
    -1.41
    ↵↵
    -1.39
    踉
    -1.39
     isu
    -1.38
     jati
    -1.36
     moro
    -1.34
     cial
    -1.31
    POSITIVE LOGITS
     a
    1.82
     for
    1.80
     peligros
    1.80
     desenli
    1.66
     blessé
    1.56
    vities
    1.55
     elbise
    1.55
     esos
    1.55
    ",
    1.55
    aving
    1.55
    Activations Density 0.002%

    No Known Activations