© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5401
    Prev
    Next
    INDEX
    Explanations

    native speaker, Strong Critics, bloody sputum

    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_16k_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
     بیشتر
    0.43
     විශ
    0.42
     شدید
    0.42
     περισσότε
    0.41
     `>`,
    0.41
    зму
    0.40
    <unused985>
    0.40
     भरपूर
    0.38
     برابر
    0.37
     ஏரா
    0.37
    POSITIVE LOGITS
    もしくは
    0.50
     kecil
    0.47
     piccole
    0.47
     pequenos
    0.46
     маленький
    0.45
    或
    0.45
     או
    0.44
     outright
    0.44
     sedikit
    0.43
     ചെറിയ
    0.43
    Activations Density 1.320%

    No Known Activations