© 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. 66039
    Prev
    Next
    INDEX
    Explanations

    configuration settings

    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
    糴
    -1.80
    ཊ
    -1.67
     asesoramiento
    -1.66
    沚
    -1.61
    力
    -1.58
     putem
    -1.55
    
    -1.55
    袛
    -1.52
     procesamiento
    -1.50
     ajustes
    -1.50
    POSITIVE LOGITS
     for
    1.95
     so
    1.80
     in
    1.63
     no
    1.55
     you
    1.44
     or
    1.41
    :
    1.38
    6
    1.36
     if
    1.34
     now
    1.33
    Activations Density 0.318%

    No Known Activations