© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65552
    Prev
    Next
    INDEX
    Explanations

    different from others

    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
     vermutlich
    -1.14
     trotz
    -1.06
     anschließend
    -0.99
    拉克
    -0.98
     eficacia
    -0.97
     eficiencia
    -0.96
    どもの
    -0.96
     erneut
    -0.96
     energías
    -0.96
     entweder
    -0.96
    POSITIVE LOGITS
     in
    4.81
     insofar
    2.58
     inasmuch
    2.14
     insom
    1.69
     In
    1.35
     حيث
    1.32
    In
    1.23
     בכ
    1.23
     في
    1.20
    wherein
    1.17
    Activations Density 0.057%

    No Known Activations