© 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. 14910
    Prev
    Next
    INDEX
    Explanations

    numbers followed by letters or quotes

    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
     daca
    -0.92
     colors
    -0.91
    °.
    -0.91
    ㅗ
    -0.91
    而去
    -0.90
    )()
    -0.90
    hskip
    -0.89
     donc
    -0.88
    château
    -0.87
    ");
    -0.86
    POSITIVE LOGITS
    woners
    1.04
    ẤT
    1.00
     sowohl
    0.99
     Tues
    0.98
    iotto
    0.98
    下さ
    0.97
    Filmographie
    0.94
     нужно
    0.91
     Dazu
    0.91
    šení
    0.90
    Activations Density 0.004%

    No Known Activations