© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1666
    Prev
    Next
    INDEX
    Explanations

    places in eastern Europe and Asia

    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
     Оде
    -0.86
    enyum
    -0.78
    silience
    -0.73
    дитесь
    -0.73
    Pham
    -0.71
     while
    -0.71
     Jornal
    -0.70
     inteligen
    -0.69
     Suomessa
    -0.69
     noteworthy
    -0.68
    POSITIVE LOGITS
     nessun
    0.82
    ObjectModel
    0.79
    inin
    0.78
    νος
    0.77
    cashire
    0.76
     european
    0.75
     במח
    0.74
     немец
    0.74
    部分は
    0.73
     usb
    0.73
    Activations Density 0.063%

    No Known Activations