© 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. 65717
    Prev
    Next
    INDEX
    Explanations

    iTunes, Photo, Foo Bar, commercial

    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
     de
    -1.78
     (
    -1.77
     for
    -1.75
    ’
    -1.72
    今天
    -1.72
     kind
    -1.67
     
    -1.66
     una
    -1.66
     out
    -1.63
     más
    -1.63
    POSITIVE LOGITS
     हालांकि
    1.95
    肄
    1.90
    仨
    1.88
    就可以了
    1.82
    就行了
    1.80
     añadió
    1.77
     Acest
    1.73
     sostu
    1.73
     tunik
    1.72
     現貨
    1.72
    Activations Density 0.046%

    No Known Activations