© 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-65K
    7. 53440
    Prev
    Next
    INDEX
    Explanations

    four appendages

    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_65k_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
    因为
    0.52
    인지
    0.50
    кви
    0.45
    で
    0.45
    이
    0.45
    сми
    0.44
     olmadığı
    0.44
    לו
    0.43
    தோ
    0.42
    Garden
    0.42
    POSITIVE LOGITS
     রয়েছে
    0.46
    するもの
    0.45
    .’
    0.45
     noteworthy
    0.43
     interplay
    0.43
     sicherlich
    0.42
     दिसून
    0.42
     ensues
    0.42
    🕘
    0.42
     timepiece
    0.41
    Activations Density 0.034%

    No Known Activations