© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7900
    Prev
    Next
    INDEX
    Explanations

    a specific value

    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
     ಅಥವಾ
    0.54
     hoặc
    0.54
     或
    0.53
    各类
    0.52
     или
    0.51
    或者
    0.50
     ή
    0.49
     किंवा
    0.49
    하거나
    0.48
    或
    0.48
    POSITIVE LOGITS
     einer
    0.57
     einem
    0.54
     sebuah
    0.54
     하나의
    0.50
     একটি
    0.50
     isang
    0.49
     важ
    0.49
     önemli
    0.49
     valuable
    0.49
     salah
    0.48
    Activations Density 0.441%

    No Known Activations