© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25713
    Prev
    Next
    INDEX
    Explanations

    structure or data representation

    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_31_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
    ,
    0.51
     to
    0.49
     Buffer
    0.46
     dioxide
    0.45
     arrange
    0.44
     alkal
    0.44
     toa
    0.44
     process
    0.44
     authent
    0.43
     inefficient
    0.43
    POSITIVE LOGITS
     zemlji
    0.52
    ೆಯಲ್ಲಿ
    0.52
    키
    0.50
    साद
    0.49
     янва
    0.48
     захворю
    0.47
    Sebagai
    0.46
     பண்டைய
    0.45
    ্ের
    0.44
     ላይ
    0.44
    Activations Density 0.002%

    No Known Activations