© 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. 81349
    Prev
    Next
    INDEX
    Explanations

    Mage::getModel or effect of

    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
     Cretaceous
    -0.76
     Bren
    -0.74
     Жу
    -0.72
    truct
    -0.71
     Kri
    -0.71
     target
    -0.71
     dedicada
    -0.71
     Target
    -0.69
    integral
    -0.69
     Aspen
    -0.69
    POSITIVE LOGITS
    artements
    0.76
    لط
    0.75
    mittent
    0.71
    Direccion
    0.71
    来越
    0.71
     JSC
    0.69
    نم
    0.69
    ásticas
    0.68
    ODY
    0.66
    bua
    0.66
    Activations Density 0.073%

    No Known Activations