© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10019
    Prev
    Next
    INDEX
    Explanations

    presentation materials

    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
    henko
    0.50
    并通过
    0.48
     পারস্পরিক
    0.48
    Luna
    0.46
    ⵜ
    0.46
     through
    0.45
    ónica
    0.44
    Mediterranean
    0.44
    ผ่าน
    0.43
    Kingdom
    0.43
    POSITIVE LOGITS
     बांधकाम
    0.44
     environs
    0.42
     অনন্য
    0.41
     буквы
    0.41
    ("--------
    0.41
    ถือ
    0.41
     '';
    0.40
     ακόμα
    0.39
     grandma
    0.39
     Adaptive
    0.39
    Activations Density 0.022%

    No Known Activations