© 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. 41-GEMMASCOPE-2-RES-262K
    7. 26912
    Prev
    Next
    INDEX
    Explanations

    North Atlantic Ocean entities

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    йын
    0.44
    RawContext
    0.43
    แด
    0.42
    یاں
    0.40
    пка
    0.38
    갑습니다
    0.38
    ᆷ
    0.37
    ⃖
    0.37
     openly
    0.37
    forcement
    0.37
    POSITIVE LOGITS
     Atlantic
    0.73
    Atlantic
    0.71
     atlantic
    0.68
    atlantic
    0.61
    ATL
    0.58
     Atl
    0.54
    Atl
    0.53
     ATL
    0.50
     Atlas
    0.47
     atl
    0.46
    Activations Density 0.002%

    No Known Activations