© 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. 112127
    Prev
    Next
    INDEX
    Explanations

    getting on or onto

    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
     récomp
    -1.68
    .
    -1.52
     réflé
    -1.49
     
    -1.48
     créée
    -1.47
    dsa
    -1.45
     esperamos
    -1.44
    神の
    -1.42
    䨻
    -1.41
     certainement
    -1.39
    POSITIVE LOGITS
     episodi
    1.55
    ("")){
    1.50
     albero
    1.48
     a
    1.43
    日目
    1.41
    ;
    1.41
     into
    1.39
    家
    1.38
    了
    1.37
    inemann
    1.34
    Activations Density 0.032%

    No Known Activations