© 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. 10222
    Prev
    Next
    INDEX
    Explanations

    on sunday

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

    list structure and 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
    व्यक्त
    0.16
    𝑻
    0.15
    ASSERT
    0.15
    SystemColors
    0.14
    𝗶
    0.14
    𝐧
    0.14
    𝚐
    0.14
    ρκ
    0.14
    ）。
    0.14
    。(
    0.14
    POSITIVE LOGITS
     منذ
    0.20
     dijo
    0.18
     apareció
    0.18
     […]
    0.18
     Kapitel
    0.18
    0.17
    ă
    0.17
     cerca
    0.17
     verano
    0.17
     chapitre
    0.17
    Activations Density 6.553%

    No Known Activations