© 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. 59711
    Prev
    Next
    INDEX
    Explanations

    javascript keywords and syntax

    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
    等等
    -1.05
     enseignants
    -0.87
    ではでは
    -0.86
    另
    -0.85
    IsNull
    -0.85
    cámara
    -0.85
     edição
    -0.83
     étudiants
    -0.82
     both
    -0.81
     nothing
    -0.81
    POSITIVE LOGITS
     them
    1.30
     it
    1.14
     its
    1.07
     ellos
    1.04
     eux
    0.90
     april
    0.88
    它
    0.88
     ними
    0.85
     tillsammans
    0.85
     оно
    0.84
    Activations Density 0.018%

    No Known Activations