© 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. 103473
    Prev
    Next
    INDEX
    Explanations

    SQL commands and processes

    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
     outono
    -0.82
    新的
    -0.82
     ngunit
    -0.82
    سك
    -0.80
     lisäksi
    -0.79
     termurah
    -0.79
     avulla
    -0.79
    стей
    -0.79
    कार
    -0.78
    龕
    -0.78
    POSITIVE LOGITS
    Preparazione
    0.90
     prépar
    0.85
     belongings
    0.83
    Hazardous
    0.81
     eletr
    0.81
    طيع
    0.81
     naveg
    0.80
    Pré
    0.79
     agrav
    0.79
    內容簡介
    0.79
    Activations Density 0.005%

    No Known Activations