© 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. 80680
    Prev
    Next
    INDEX
    Explanations

    layout attributes

    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
    ifikationer
    -0.80
    atoday
    -0.77
    file
    -0.70
     замі
    -0.69
    Replacing
    -0.68
    Ша
    -0.67
    Digital
    -0.67
    卹
    -0.67
    thra
    -0.66
    Correo
    -0.65
    POSITIVE LOGITS
    營養
    0.66
     Secondary
    0.63
    anthene
    0.62
     disbelief
    0.61
    اتر
    0.60
     четвер
    0.60
     faculty
    0.60
     Gibson
    0.59
    父の
    0.59
    찼
    0.59
    Activations Density 0.086%

    No Known Activations