© 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. 46410
    Prev
    Next
    INDEX
    Explanations

    crusher used, during September, supplier

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

    special characters or formatting

    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
    𝑪
    0.47
     দায়িত্ব
    0.45
     জানিয়েছিলেন
    0.45
    式的
    0.45
     insecure
    0.45
    𝑰
    0.45
     плат
    0.44
     দিয়েছিলেন
    0.43
    DID
    0.43
    是因为
    0.42
    POSITIVE LOGITS
     doświad
    0.52
     Lebens
    0.48
     протягом
    0.47
     नाही
    0.47
     Š
    0.47
     neonatal
    0.46
     경험
    0.46
     ją
    0.45
     성능
    0.45
     funkcjon
    0.44
    Activations Density 0.000%

    No Known Activations