© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109430
    Prev
    Next
    INDEX
    Explanations

    wool orient, clearly could, development and

    np_acts-logits-general · gemini-2.5-flash-lite

    prediction accuracy and reduces artifacts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dentées
    0.49
    tempHeader
    0.44
     свет
    0.44
     項
    0.44
     générale
    0.44
     долларов
    0.44
     ডলার
    0.42
     света
    0.42
    ($("#
    0.42
     функций
    0.42
    POSITIVE LOGITS
     deliverables
    0.45
     PU
    0.44
     Yukarı
    0.44
    Exerc
    0.44
    PU
    0.43
     Peker
    0.43
     deliveries
    0.43
    і
    0.42
     PUC
    0.42
    Deliver
    0.41
    Activations Density 0.000%

    No Known Activations