© 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. 2397
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols

    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
    嘱
    -0.91
    gén
    -0.76
    iliano
    -0.76
     सर
    -0.72
    нял
    -0.72
    ETHYL
    -0.71
    semp
    -0.71
    aturing
    -0.71
    TRIBUT
    -0.71
    ajaan
    -0.69
    POSITIVE LOGITS
     uovo
    0.90
     Sección
    0.85
     chanteur
    0.84
     Réponses
    0.80
    ogna
    0.79
     Donations
    0.77
     entendimiento
    0.77
    yah
    0.76
     Solution
    0.75
    집
    0.75
    Activations Density 0.011%

    No Known Activations