© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24879
    Prev
    Next
    INDEX
    Explanations

    former or repurposed buildings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     civilized
    0.42
     hypothetical
    0.41
    ্যেষ্ঠ
    0.41
     crowded
    0.39
     counseling
    0.39
     downhill
    0.39
     computerized
    0.39
     भीड़
    0.38
     കർ
    0.37
    (".");
    0.37
    POSITIVE LOGITS
     former
    1.05
    former
    1.02
    Former
    1.00
     Former
    0.97
     ehemaligen
    0.94
     býval
    0.93
     repurposed
    0.91
     ehemalige
    0.91
     bekas
    0.88
     antiguas
    0.86
    Activations Density 0.009%

    No Known Activations