© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7358
    Prev
    Next
    INDEX
    Explanations

    two items

    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
    <unused972>
    0.23
     แต
    0.22
     להיות
    0.22
    โยชน์
    0.22
     تمامی
    0.22
     נישט
    0.21
     wyt
    0.21
     anvä
    0.21
     mendatang
    0.21
     повинні
    0.21
    POSITIVE LOGITS
     two
    0.32
    ва
    0.31
    兩個
    0.30
     două
    0.29
    两个
    0.29
     beiden
    0.29
    з
    0.29
    两
    0.29
     రెండు
    0.28
    وم
    0.28
    Activations Density 0.216%

    No Known Activations