© 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. 3135
    Prev
    Next
    INDEX
    Explanations

    Washington Post

    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
    ียม
    -0.80
     długość
    -0.78
    级的
    -0.72
     frock
    -0.72
     wicket
    -0.71
     cosp
    -0.71
     Eura
    -0.69
    Бер
    -0.68
    дии
    -0.68
     trough
    -0.68
    POSITIVE LOGITS
    Shown
    0.89
     shown
    0.81
    shown
    0.78
    сут
    0.75
    стат
    0.74
    ~~~
    0.74
     与
    0.74
    Mey
    0.73
    Manager
    0.72
    waarden
    0.72
    Activations Density 0.094%

    No Known Activations