© 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. 117095
    Prev
    Next
    INDEX
    Explanations

    Exclusive collection, foreign exchange, two federal

    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
    utnik
    -0.81
    rektur
    -0.76
    Ингредиенты
    -0.75
    queo
    -0.74
    outro
    -0.73
    Юлия
    -0.73
    ַל
    -0.70
    IRQn
    -0.69
    نى
    -0.69
     鐵
    -0.69
    POSITIVE LOGITS
     путь
    0.79
     resume
    0.78
     تمامی
    0.77
     WY
    0.73
     plutôt
    0.73
     quas
    0.71
     briefcase
    0.71
    ∝
    0.71
    bb
    0.71
    rather
    0.71
    Activations Density 0.027%

    No Known Activations