© 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. 123677
    Prev
    Next
    INDEX
    Explanations

    you are

    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
     Apalagi
    -1.63
     自分
    -1.60
     with
    -1.57
    んご
    -1.53
     笑顔
    -1.52
     仕事
    -1.49
     Schluß
    -1.42
     same
    -1.42
    一个小
    -1.41
     Sedangkan
    -1.41
    POSITIVE LOGITS
     \
    1.57
     {
    1.48
    ве
    1.47
     mereka
    1.44
    |}
    1.41
    begin
    1.40
     If
    1.39
    нему
    1.37
    __('
    1.36
    {~
    1.35
    Activations Density 0.058%

    No Known Activations