© 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. 176436
    Prev
    Next
    INDEX
    Explanations

    money, Judah, defeated, Zachary

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

    words about encouragement

    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
     NO
    0.49
     II
    0.49
    ä
    0.48
     동시에
    0.47
     SONG
    0.45
     WAT
    0.44
    nu
    0.43
    vspace
    0.43
     본
    0.43
     PAS
    0.43
    POSITIVE LOGITS
    لې
    0.50
    ிட்ட
    0.50
    leiter
    0.50
     difund
    0.50
    اك
    0.50
     apoyar
    0.49
    Toolkit
    0.48
    WebGL
    0.47
     руководитель
    0.47
    ارب
    0.47
    Activations Density 0.000%

    No Known Activations