© 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. 40-GEMMASCOPE-2-RES-65K
    7. 53638
    Prev
    Next
    INDEX
    Explanations

    white color code

    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_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
     beyaz
    0.46
     whitish
    0.46
     white
    0.44
    白
    0.44
     trắng
    0.43
     सफेद
    0.42
     સફેદ
    0.42
     سفید
    0.41
     белый
    0.41
    白色
    0.41
    POSITIVE LOGITS
    inton
    0.41
    aldas
    0.40
     []
    0.39
    iswa
    0.37
     בח
    0.37
     bis
    0.37
    algorith
    0.37
     Juden
    0.36
     shale
    0.36
    ala
    0.35
    Activations Density 0.007%

    No Known Activations