© 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. 90334
    Prev
    Next
    INDEX
    Explanations

    insertion into openings or spaces

    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
    Siapa
    -0.83
     immense
    -0.77
    ABOUT
    -0.75
    sibilità
    -0.75
     rentable
    -0.73
    unlike
    -0.73
    
    -0.73
     Shari
    -0.72
    rateur
    -0.72
    NEG
    -0.72
    POSITIVE LOGITS
     slots
    2.36
     slot
    2.27
    slots
    1.81
    Slot
    1.72
    slot
    1.71
     Slot
    1.70
     Slots
    1.69
     sockets
    1.68
    Slots
    1.57
     socket
    1.55
    Activations Density 0.100%

    No Known Activations