© 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. 26196
    Prev
    Next
    INDEX
    Explanations

    condensed milk

    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
    })_{\
    0.39
    糯
    0.39
    salt
    0.39
     glut
    0.38
    墠
    0.38
     рабочего
    0.38
    sweet
    0.37
     reconstit
    0.37
    broad
    0.37
    Palm
    0.37
    POSITIVE LOGITS
    bordered
    0.51
    Condensed
    0.46
     striped
    0.45
    hover
    0.45
     condensed
    0.45
    飚
    0.44
     Condensed
    0.44
     bordered
    0.43
     condos
    0.43
    BORDER
    0.42
    Activations Density 0.001%

    No Known Activations