© 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. 228101
    Prev
    Next
    INDEX
    Explanations

    Attached column

    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
     MediaPlayer
    0.45
    ара
    0.44
    इंट
    0.44
     всей
    0.42
    ơi
    0.41
     όλ
    0.41
    ౖ
    0.41
    зим
    0.41
    ẹp
    0.40
     Nursing
    0.40
    POSITIVE LOGITS
    鳟
    0.44
     according
    0.44
    carte
    0.44
    体
    0.42
    オート
    0.42
    ตาม
    0.41
    断
    0.41
     نر
    0.41
    정이
    0.39
    定
    0.39
    Activations Density 0.001%

    No Known Activations