© 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. 83100
    Prev
    Next
    INDEX
    Explanations

    data binding and grids

    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
    dań
    -0.79
    diocese
    -0.75
    hlands
    -0.75
    шают
    -0.74
    unyi
    -0.74
    disks
    -0.73
    tructive
    -0.73
    itudinal
    -0.72
    sizing
    -0.72
    lauf
    -0.72
    POSITIVE LOGITS
     bound
    0.89
    reactor
    0.79
     Bound
    0.75
    Bound
    0.74
    CONNECTION
    0.71
     Iq
    0.71
     aware
    0.70
     table
    0.69
    Wah
    0.69
     binds
    0.69
    Activations Density 0.042%

    No Known Activations