© 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. 107731
    Prev
    Next
    INDEX
    Explanations

    Copyright and license information

    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
    arthur
    -0.79
    parametrize
    -0.77
     characteristics
    -0.77
     raining
    -0.76
     for
    -0.75
    当初
    -0.73
    人に
    -0.72
     đua
    -0.71
    ">'+
    -0.71
     low
    -0.71
    POSITIVE LOGITS
    entrée
    1.00
    但也
    0.90
    ģ
    0.89
     Ло
    0.88
    бах
    0.86
    nek
    0.85
     relativement
    0.84
     Ко
    0.83
     tâ
    0.81
     На
    0.81
    Activations Density 0.029%

    No Known Activations