© 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. 16-GEMMASCOPE-2-RES-262K
    7. 145502
    Prev
    Next
    INDEX
    Explanations

    socially necessary labor, Temple gardens, Cutie Mark, Douglas, 兵马俑, Hoisin

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    км
    0.56
    кой
    0.55
    මණ
    0.53
     européens
    0.53
     ጣ
    0.50
    单一
    0.50
    лм
    0.50
     árabe
    0.50
     Europese
    0.49
    Ს
    0.48
    POSITIVE LOGITS
     commentator
    0.48
     Swain
    0.45
     vais
    0.44
     coinvol
    0.44
     Faire
    0.43
     જોઈએ
    0.42
     Machine
    0.42
    faire
    0.41
     t
    0.41
     transplanted
    0.41
    Activations Density 0.000%

    No Known Activations