© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132
    Prev
    Next
    INDEX
    Explanations

    black color

    np_acts-logits-general · gemini-2.5-flash-lite

    dark colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.62
     bạn
    0.54
     breaths
    0.54
     bậc
    0.52
     Krista
    0.52
    આ
    0.52
    ير
    0.52
    {
    0.52
    उत्तर
    0.51
    एम
    0.50
    POSITIVE LOGITS
    black
    1.45
     কালো
    1.45
     black
    1.44
    黑
    1.42
     darker
    1.37
     黒
    1.36
     чор
    1.34
     BLACK
    1.32
     Black
    1.31
    黑色
    1.31
    Activations Density 0.095%

    No Known Activations