© 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. 30708
    Prev
    Next
    INDEX
    Explanations

    scientific notation

    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
     options
    0.49
    蚝
    0.46
    飒
    0.45
     seçenek
    0.44
     January
    0.42
    价格
    0.41
     prices
    0.41
    选项
    0.41
    ావ
    0.41
     Vanilla
    0.40
    POSITIVE LOGITS
     mism
    0.45
    OLYBD
    0.44
    ]-\
    0.39
    VIII
    0.38
     mismatch
    0.37
     mier
    0.37
     mismatched
    0.37
     stali
    0.37
    NOWLEDGE
    0.36
     lagen
    0.36
    Activations Density 0.020%

    No Known Activations