© 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. 55890
    Prev
    Next
    INDEX
    Explanations

    foreign language identifiers

    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
     oper
    0.46
     botanical
    0.43
    巢
    0.43
     throughput
    0.43
    و
    0.43
     manual
    0.42
     parliamentary
    0.42
    ऊ
    0.42
     longitudinal
    0.42
    ちゃんと
    0.41
    POSITIVE LOGITS
     ਤੁਹਾ
    0.44
    extras
    0.44
     говори
    0.43
     Ва
    0.42
     ବି
    0.41
     か
    0.41
    চাঁ
    0.40
     зависи
    0.39
     ይመ
    0.39
     из
    0.39
    Activations Density 0.003%

    No Known Activations