© 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. 40-GEMMASCOPE-2-RES-262K
    7. 137037
    Prev
    Next
    INDEX
    Explanations

    building hierarchies or systems

    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
    Not in Any Lists

    No Comments

    Negative Logits
     слы
    0.46
    भर
    0.41
    㬹
    0.39
    rawl
    0.38
     消
    0.38
    パリ
    0.37
     किफ
    0.37
     एमबी
    0.37
    ња
    0.36
    錡
    0.36
    POSITIVE LOGITS
     Younger
    0.42
     Yourself
    0.41
     Nu
    0.40
     Living
    0.39
    Nu
    0.39
     Women
    0.39
     tomatoes
    0.38
     Ko
    0.38
     yourself
    0.37
    tti
    0.37
    Activations Density 0.003%

    No Known Activations