© 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. 47855
    Prev
    Next
    INDEX
    Explanations

    data size units (KB, MB, GB)

    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
     only
    -0.92
     horas
    -0.83
     Only
    -0.80
     години
    -0.78
    季
    -0.76
     только
    -0.75
    utm
    -0.73
    脚注の使い方
    -0.72
     muy
    -0.72
     mas
    -0.72
    POSITIVE LOGITS
     MB
    1.33
    MB
    1.23
    mb
    1.10
     KB
    1.08
     Mb
    1.02
    Mb
    1.02
     kb
    1.00
     Meg
    0.98
    kb
    0.98
     rami
    0.95
    Activations Density 0.041%

    No Known Activations