© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2921
    Prev
    Next
    INDEX
    Explanations

    United States

    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
    girl
    -0.75
    slf
    -0.71
     ایالات
    -0.70
    áni
    -0.69
    rety
    -0.69
     внутренних
    -0.69
    andidat
    -0.67
    Neither
    -0.67
    chips
    -0.65
    liers
    -0.65
    POSITIVE LOGITS
    cuador
    0.72
     script
    0.71
    плю
    0.69
    явля
    0.64
     legible
    0.63
     جوان
    0.63
    邋
    0.63
     colgantes
    0.62
    tazione
    0.62
     leakage
    0.62
    Activations Density 0.055%

    No Known Activations