© 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. 235406
    Prev
    Next
    INDEX
    Explanations

    linked toexecute instructionssecond quarter worthdefines comprises of

    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
    тьми
    0.49
    τισ
    0.46
    ظم
    0.46
     yeter
    0.46
    теры
    0.44
    촐
    0.43
     liberté
    0.43
    ర్లు
    0.43
     kullanılır
    0.43
     собственности
    0.43
    POSITIVE LOGITS
    ↵
    0.48
     Our
    0.46
    すなわち
    0.45
     Again
    0.43
    ↵↵↵↵
    0.42
              
    0.42
     Wall
    0.42
     অর্থাৎ
    0.42
     म्हणजेच
    0.42
     壁
    0.40
    Activations Density 0.000%

    No Known Activations