© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129050
    Prev
    Next
    INDEX
    Explanations

    tiny part

    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
    Negative Logits
    人材
    0.48
    クレジット
    0.47
    사랑
    0.46
    LOVE
    0.45
     طریق
    0.44
    防災
    0.44
     再
    0.43
    әй
    0.43
     lại
    0.43
    らく
    0.43
    POSITIVE LOGITS
    Calculate
    0.42
    Determine
    0.42
     Usage
    0.41
     Clone
    0.41
     Initialize
    0.40
     Cane
    0.40
    etre
    0.39
    নমেন্ট
    0.38
    allowing
    0.38
     Use
    0.37
    Activations Density 0.002%

    No Known Activations