© 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. 90773
    Prev
    Next
    INDEX
    Explanations

    selector, event, licence

    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
    coda
    -0.79
    bras
    -0.71
    ibos
    -0.70
    落
    -0.69
    ingh
    -0.68
     Stand
    -0.66
    uyen
    -0.66
     الرح
    -0.66
    asant
    -0.66
     Стан
    -0.65
    POSITIVE LOGITS
    Peripheral
    0.75
     PARAMETERS
    0.72
    certificates
    0.70
    happened
    0.70
    acquired
    0.69
    jsonArray
    0.69
     bañera
    0.68
    peripheral
    0.68
     dommage
    0.68
    indelijk
    0.66
    Activations Density 0.049%

    No Known Activations