© 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. 40-GEMMASCOPE-2-RES-262K
    4. 21513
    Prev
    Next
    INDEX
    Explanations

    unusual, unique, unconventional

    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
    閡
    0.40
    Roboto
    0.39
    많은
    0.37
     आटे
    0.36
     బాధ
    0.36
     Roboto
    0.36
    大好き
    0.35
    懦
    0.35
    끓
    0.34
    懊
    0.34
    POSITIVE LOGITS
     unusual
    2.69
     unconventional
    2.58
     необы
    2.45
     Unusual
    2.42
     unorthodox
    2.42
     atypical
    1.97
     uncommon
    1.92
     असामान्य
    1.89
     unique
    1.78
     ungew
    1.74
    Activations Density 0.036%

    No Known Activations