© 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. 13160
    Prev
    Next
    INDEX
    Explanations

    future possibility or necessity

    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
     were
    -1.72
     that
    -1.70
    中国的
    -1.63
    
    -1.58
     with
    -1.47
    ка
    -1.44
    d
    -1.40
    ки
    -1.38
    но
    -1.38
     hura
    -1.37
    POSITIVE LOGITS
    
    1.97
    艿
    1.68
     meines
    1.66
     to
    1.59
    Mainly
    1.54
     приходится
    1.54
     biraz
    1.53
    engg
    1.52
    合う
    1.49
     taky
    1.49
    Activations Density 0.007%

    No Known Activations