© 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. 154614
    Prev
    Next
    INDEX
    Explanations

    shampoo bottles

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

    accuracy of Regex

    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
    $),
    0.47
    鑲
    0.46
    婇
    0.46
    AG
    0.46
     allí
    0.45
    INUS
    0.45
    品種
    0.45
     limitaciones
    0.44
    лож
    0.44
     moneda
    0.43
    POSITIVE LOGITS
     firewall
    0.52
    segn
    0.51
     दिलाने
    0.48
     谢
    0.46
     वाली
    0.45
     transmissions
    0.45
     oven
    0.45
     gaping
    0.45
     transmission
    0.44
     pyl
    0.44
    Activations Density 0.000%

    No Known Activations