© 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. 75838
    Prev
    Next
    INDEX
    Explanations

    Qt UI elements

    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
     pozna
    -0.76
     reactie
    -0.73
    LinkedHashMap
    -0.73
     Blume
    -0.73
     spettacolo
    -0.73
    lwjgl
    -0.73
     azeite
    -0.72
    Források
    -0.72
    GND
    -0.72
    /:
    -0.71
    POSITIVE LOGITS
    Spacing
    0.84
    addWidget
    0.79
     Doha
    0.77
     Q
    0.76
     Spacing
    0.75
     spacer
    0.74
    ayout
    0.73
    kého
    0.73
    тием
    0.72
     공
    0.71
    Activations Density 0.001%

    No Known Activations