© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203896
    Prev
    Next
    INDEX
    Explanations

    themes and abstract concepts

    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_31_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
     Zustimmung
    0.46
    损害
    0.46
     Ли
    0.45
    نوع
    0.40
    න්ද
    0.40
    ющих
    0.39
    اند
    0.38
    杨
    0.38
    বা
    0.37
    书籍
    0.37
    POSITIVE LOGITS
     mutta
    0.51
     絶対
    0.48
    ⌣
    0.46
     tycker
    0.45
    льність
    0.45
    ņ
    0.45
     แต่
    0.45
     badges
    0.45
    setdefault
    0.44
     เอา
    0.44
    Activations Density 0.002%

    No Known Activations