© 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. 31-GEMMASCOPE-2-RES-262K
    7. 80189
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and classifications

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    شرين
    0.51
    voiced
    0.48
    天
    0.47
    إ
    0.46
    天下
    0.46
    太阳
    0.45
    тан
    0.44
    는
    0.44
    àu
    0.43
    вов
    0.42
    POSITIVE LOGITS
     flowchart
    0.49
     Abst
    0.46
     enumer
    0.46
     Ballot
    0.44
     analogous
    0.44
     ASCII
    0.43
     Bibliography
    0.43
     Punishment
    0.43
     Threshold
    0.42
     DDT
    0.42
    Activations Density 0.003%

    No Known Activations