© 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. 84193
    Prev
    Next
    INDEX
    Explanations

    Spring framework and place names

    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
    delt
    -0.76
    mento
    -0.76
    平凡
    -0.75
     wizard
    -0.75
    */,
    -0.74
     flight
    -0.73
     vuotta
    -0.73
     comedor
    -0.73
     stata
    -0.72
    Scrolling
    -0.72
    POSITIVE LOGITS
     SPRING
    0.84
    Spring
    0.84
     springing
    0.83
     chiam
    0.81
     меро
    0.80
     Spring
    0.79
     khaki
    0.77
     sprung
    0.77
     полови
    0.77
     soiled
    0.75
    Activations Density 0.019%

    No Known Activations