© 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-262K
    7. 29178
    Prev
    Next
    INDEX
    Explanations

    word beginnings followed by punctuation

    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_262k_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
     एंट्रेंस
    0.54
     पांडेय
    0.52
     개선
    0.47
    ंदन
    0.47
     heterogeneity
    0.45
    ioxid
    0.44
     መድሃኒ
    0.44
    溱
    0.43
    Assured
    0.43
     स्क्रीनिंग
    0.42
    POSITIVE LOGITS
     peut
    0.48
     stries
    0.46
     creates
    0.45
     može
    0.43
     stamped
    0.43
     Türkiye
    0.42
    은
    0.41
     octobre
    0.41
     может
    0.40
     may
    0.40
    Activations Density 0.001%

    No Known Activations