© 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. 22-GEMMASCOPE-RES-131K
    7. 27157
    Prev
    Next
    INDEX
    Explanations

    George Will names or titles

    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_22/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
    ヌード
    -1.05
    合わない
    -1.02
     endblock
    -0.94
     ennen
    -0.93
    żyć
    -0.93
    loat
    -0.91
    putation
    -0.90
     оружи
    -0.90
    jach
    -0.90
     prevé
    -0.89
    POSITIVE LOGITS
    ִים
    0.99
    wyżs
    0.98
     vielmehr
    0.97
    اي
    0.96
    ผม
    0.95
    ganu
    0.93
    ículas
    0.93
    mış
    0.93
     otor
    0.90
     continuously
    0.90
    Activations Density 0.001%

    No Known Activations