© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56545
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_acts-logits-general · gemini-2.5-flash-lite

    German and English phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ادم
    0.51
    وق
    0.50
    لاق
    0.49
    اس
    0.49
     diox
    0.48
     developmental
    0.46
    وغ
    0.46
    都
    0.46
     blitz
    0.45
    الم
    0.44
    POSITIVE LOGITS
     เสียง
    0.52
    ेंशियल
    0.50
    വില്‍
    0.50
     প্রতি
    0.48
     chciał
    0.48
     ngon
    0.48
     nữa
    0.48
     najbli
    0.47
     presenti
    0.47
    ClearedBy
    0.46
    Activations Density 0.000%

    No Known Activations