© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28138
    Prev
    Next
    INDEX
    Explanations

    plt.subplots and figure plotting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    фици
    0.45
    ست
    0.37
    ieb
    0.37
     »,
    0.36
    ጐ
    0.36
     مض
    0.36
    셋
    0.36
    미
    0.35
    তরে
    0.34
     Rica
    0.34
    POSITIVE LOGITS
     glove
    0.40
    subequations
    0.39
     ампли
    0.37
     prototyping
    0.37
     wcout
    0.36
     Fourier
    0.36
     articulated
    0.36
    чат
    0.35
     خوشه
    0.35
     জুটি
    0.35
    Activations Density 0.000%

    No Known Activations