© 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. 65814
    Prev
    Next
    INDEX
    Explanations

    numbers and time calculations

    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
     backing
    -1.27
     backwards
    -1.20
     backed
    -1.13
     backward
    -1.12
    backed
    -1.08
    backward
    -1.07
    后退
    -1.07
    backing
    -1.07
    Backing
    -1.06
     backs
    -1.04
    POSITIVE LOGITS
    都市
    0.77
    ZAN
    0.75
    existe
    0.75
    漫
    0.73
    maries
    0.73
     Ciencia
    0.71
     Barnard
    0.71
     moron
    0.71
     JY
    0.71
     retorn
    0.70
    Activations Density 0.038%

    No Known Activations