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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 6160
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and states

    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_65k_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
    └──
    0.47
    ociaż
    0.39
     innych
    0.38
    finalize
    0.37
    也是
    0.36
     anderen
    0.35
    ալ
    0.35
     może
    0.35
     др
    0.35
    autres
    0.34
    POSITIVE LOGITS
    німа
    0.36
     सगळे
    0.36
     выпа
    0.35
    逓
    0.33
     \[
    0.32
    鏻
    0.32
    Qu
    0.32
    غط
    0.31
     Diocese
    0.31
    льність
    0.31
    Activations Density 0.276%

    No Known Activations