© 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. 26174
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     decompression
    0.40
    ','"
    0.39
     Component
    0.38
    ｀
    0.38
     fome
    0.38
     ಕೂಡ
    0.38
    RadioButton
    0.37
    乂
    0.37
     Букови
    0.37
    碚
    0.37
    POSITIVE LOGITS
     Gareth
    0.51
     Frances
    0.47
     Kirsten
    0.45
     Josh
    0.44
     Deepak
    0.44
    osh
    0.44
     Dominic
    0.43
     David
    0.42
     Brian
    0.42
     Stephen
    0.41
    Activations Density 0.000%

    No Known Activations