© 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. 109493
    Prev
    Next
    INDEX
    Explanations

    layout dimensions

    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
    although
    -1.00
     MASSACHUSETTS
    -0.97
    Although
    -0.91
     dağı
    -0.89
     THOUGH
    -0.89
     voork
    -0.87
     marzo
    -0.87
    INGREDIENTES
    -0.86
     RELATIONSHIP
    -0.86
     Although
    -0.86
    POSITIVE LOGITS
    SizedBox
    1.38
     SizedBox
    1.36
     gaps
    0.91
     wysokości
    0.88
     gap
    0.87
     space
    0.85
     فاصله
    0.85
     vinte
    0.84
     небольшой
    0.83
    sized
    0.82
    Activations Density 0.000%

    No Known Activations