© 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. 143796
    Prev
    Next
    INDEX
    Explanations

    reproduce, behalf, sustained

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

    empires rise and fall

    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
    oszt
    0.50
    م
    0.50
    只有一个
    0.49
    aglia
    0.49
     முழுக்க
    0.49
    类型的
    0.48
    śla
    0.46
    ză
    0.46
    м
    0.46
    është
    0.45
    POSITIVE LOGITS
     febrero
    0.58
    क्‍
    0.54
     productos
    0.51
     Supervisors
    0.49
     supervisors
    0.48
     professores
    0.48
     THEM
    0.48
     antifungal
    0.47
     fprintf
    0.46
     especialmente
    0.46
    Activations Density 0.000%

    No Known Activations