© 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. 46431
    Prev
    Next
    INDEX
    Explanations

    End of sentence keywords: NE, Population, Total

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

    Fats NFTs Original Witness

    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
     انتہائی
    0.50
     والت
    0.48
    练习
    0.46
     단순히
    0.45
    ,
    0.43
    Мушко
    0.43
     여기에
    0.42
     coursework
    0.42
    是通过
    0.42
    同时也
    0.42
    POSITIVE LOGITS
    εκ
    0.53
     ждать
    0.51
     racemic
    0.45
    caria
    0.44
    ฺ
    0.44
    সময়
    0.43
     Morin
    0.43
     hasta
    0.43
     Kaz
    0.42
     antigens
    0.42
    Activations Density 0.000%

    No Known Activations