© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13877
    Prev
    Next
    INDEX
    Explanations

    numbers, lists, and sections

    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
     عادة
    0.45
     معمول
    0.44
     Анастасия
    0.40
    ഈ
    0.40
    uradaki
    0.39
     보통
    0.38
    मुख्य
    0.36
    正确的
    0.36
     Normally
    0.35
    Usually
    0.35
    POSITIVE LOGITS
     projects
    0.40
     toa
    0.38
     that
    0.38
     which
    0.38
     h
    0.37
     profiles
    0.37
    θηκαν
    0.36
     whose
    0.36
     campaigns
    0.36
     portfolios
    0.36
    Activations Density 0.302%

    No Known Activations