© 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. 34-GEMMASCOPE-RES-131K
    7. 111036
    Prev
    Next
    INDEX
    Explanations

    seeking explanations as to

    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_34/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
     concorda
    -0.98
    uró
    -0.98
     promove
    -0.93
     defekt
    -0.88
     cuida
    -0.85
     behar
    -0.85
    :^{
    -0.84
     mudou
    -0.84
    ждают
    -0.82
     gostar
    -0.82
    POSITIVE LOGITS
     as
    4.81
    至于
    1.97
     regarding
    1.91
     about
    1.88
     как
    1.63
    as
    1.59
    至於
    1.56
     As
    1.55
    As
    1.52
     ως
    1.34
    Activations Density 0.119%

    No Known Activations