© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 103167
    Prev
    Next
    INDEX
    Explanations

    last names, human feedback, route, layer

    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
    Not in Any Lists

    No Comments

    Negative Logits
     trainers
    0.37
     createArticle
    0.36
     ช่อง
    0.36
    蛻
    0.36
     เ
    0.35
    Getty
    0.35
     Tread
    0.34
     도입
    0.34
     통해
    0.34
     Потому
    0.34
    POSITIVE LOGITS
    Ads
    0.43
    ்டர்
    0.41
     estrict
    0.41
    柔らか
    0.40
    飫
    0.40
    できない
    0.40
     Oso
    0.40
     hafif
    0.39
     Pich
    0.39
     slight
    0.39
    Activations Density 0.776%

    No Known Activations