© 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. 85612
    Prev
    Next
    INDEX
    Explanations

    codes and passwords

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

    divine status, music, and finances

    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
     poten
    0.54
    то
    0.51
    தா
    0.51
     españ
    0.50
    Ꮏ
    0.50
     Astrophysics
    0.48
     potenz
    0.48
     potencial
    0.47
     между
    0.46
    荭
    0.46
    POSITIVE LOGITS
     ねえ
    0.52
     편
    0.46
     휴
    0.46
    </h3>
    0.45
     मिळा
    0.45
     매우
    0.45
     GLUT
    0.45
    pieces
    0.45
    palette
    0.45
     cleanse
    0.45
    Activations Density 0.000%

    No Known Activations