© 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. 130157
    Prev
    Next
    INDEX
    Explanations

    need to do something

    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
    ")){
    -1.71
     oignon
    -1.57
     "";
    -1.48
    ίας
    -1.48
    ;}
    -1.45
     <<<<<<<<<<<<<<
    -1.40
    悒
    -1.39
    ные
    -1.38
    льності
    -1.38
    件事情
    -1.36
    POSITIVE LOGITS
     should
    2.02
     would
    1.75
     is
    1.59
     need
    1.55
    还是要
    1.53
     could
    1.41
     has
    1.40
    正好
    1.40
    {
    1.38
     ia
    1.36
    Activations Density 0.047%

    No Known Activations