© 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. 111028
    Prev
    Next
    INDEX
    Explanations

    hardware events or modules

    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
    UMENT
    -0.84
     Transmitter
    -0.80
    ISR
    -0.78
    ོ་
    -0.77
     curly
    -0.75
     hornblende
    -0.74
     .;
    -0.73
     schuhe
    -0.72
     oysters
    -0.71
     OY
    -0.71
    POSITIVE LOGITS
     timer
    0.84
     crypto
    0.83
     Event
    0.83
    Unused
    0.78
     External
    0.77
     external
    0.77
    éné
    0.77
     peripheral
    0.77
     audio
    0.75
     Ethernet
    0.75
    Activations Density 0.037%

    No Known Activations