© 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. 16-GEMMASCOPE-2-RES-262K
    7. 116071
    Prev
    Next
    INDEX
    Explanations

    specific terms

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ነው።
    0.58
    ል።
    0.52
    starcore
    0.50
    *>
    0.50
     disparu
    0.50
     scandals
    0.49
     使っ
    0.49
     Gericht
    0.49
    GBuf
    0.49
     intervento
    0.49
    POSITIVE LOGITS
    Configurations
    0.53
    essen
    0.51
    ores
    0.46
    ids
    0.44
    immen
    0.44
    ו
    0.44
    checklist
    0.43
    语
    0.43
    ressed
    0.42
    灵
    0.42
    Activations Density 0.000%

    No Known Activations