© 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-16K
    7. 9294
    Prev
    Next
    INDEX
    Explanations

    code, numbers, and punctuation

    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_16k_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
    সুতরাং
    0.22
     discapacidad
    0.21
     সুতরাং
    0.21
     অতএব
    0.21
     وبالتالي
    0.20
    偻
    0.20
    公益
    0.20
     ভিক্ষ
    0.20
    榄
    0.20
     creencias
    0.20
    POSITIVE LOGITS
    umbling
    0.23
     gotovo
    0.22
     distinguish
    0.21
     neuen
    0.21
     बहुतेक
    0.21
     distinction
    0.21
     जेव्हा
    0.21
     допомогою
    0.20
     લગભગ
    0.20
     કેટલાક
    0.20
    Activations Density 0.030%

    No Known Activations