© 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. 43657
    Prev
    Next
    INDEX
    Explanations

    page paths and imports

    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
     used
    -1.79
     When
    -1.70
     one
    -1.68
    ).
    -1.62
     may
    -1.55
     on
    -1.55
     use
    -1.54
     previous
    -1.52
     help
    -1.52
     our
    -1.50
    POSITIVE LOGITS
    Новые
    1.68
     Mijn
    1.66
    ㍑
    1.59
    ープン
    1.58
    
    1.53
     journaliste
    1.53
    鉺
    1.53
     acteurs
    1.52
    幛
    1.52
     YANG
    1.52
    Activations Density 0.006%

    No Known Activations