© 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. 4555
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    0.61
     attenzione
    0.50
    ка
    0.48
     অনেকে
    0.43
     আগুন
    0.39
     ד
    0.39
    อัน
    0.38
    }",
    0.38
     pokud
    0.38
    기
    0.38
    POSITIVE LOGITS
    니스
    0.50
    maßen
    0.49
     असलेल्या
    0.49
    ोनेशिया
    0.48
     NYSE
    0.48
    म्मा
    0.46
     किंग्स
    0.45
    어졌
    0.45
     Keychain
    0.45
    라이언트
    0.45
    Activations Density 0.029%

    No Known Activations