© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 190579
    Prev
    Next
    INDEX
    Explanations

    words after select, out, or to

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

    codes and abbreviations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    チャレンジ
    0.50
     середине
    0.49
    이드
    0.46
    喈
    0.46
    challeng
    0.43
    Conteudos
    0.42
    enfant
    0.42
    鋳
    0.41
     местные
    0.41
    uencias
    0.41
    POSITIVE LOGITS
    عت
    0.49
    ged
    0.45
    matically
    0.42
    slides
    0.42
     तरी
    0.41
    ত্ত্ব
    0.41
    xl
    0.40
     SUVs
    0.40
    （
    0.40
    zed
    0.40
    Activations Density 0.001%

    No Known Activations