© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40302
    Prev
    Next
    INDEX
    Explanations

    localization and text formatting

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

    qualities or imperfections

    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
     मोर्चा
    0.40
    ও
    0.39
    どの
    0.38
    是一種
    0.37
    部份
    0.36
    、「
    0.36
    。。。。
    0.36
    ‥
    0.36
    。。。
    0.35
    銚
    0.35
    POSITIVE LOGITS
     இன்று
    0.40
     varsa
    0.40
     सुर्खियों
    0.39
     जास्त
    0.39
     ఉంట
    0.38
    不断
    0.38
     люблю
    0.38
     लाइसेंस
    0.38
     少
    0.38
     நிறைய
    0.38
    Activations Density 0.002%

    No Known Activations