© 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. 12896
    Prev
    Next
    INDEX
    Explanations

    examples involving lists or code

    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
    Ⲓ
    0.46
    毽
    0.46
    鹼
    0.45
     січня
    0.45
    マネ
    0.44
    ಲ್ಲು
    0.44
    एचओ
    0.44
     murid
    0.43
    끄
    0.43
    IDADES
    0.43
    POSITIVE LOGITS
    ad
    0.46
     Almighty
    0.46
    row
    0.45
     A
    0.45
    ante
    0.43
    an
    0.42
     Gear
    0.42
     Authority
    0.42
     Promises
    0.42
     authority
    0.41
    Activations Density 0.014%

    No Known Activations