© 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. 93676
    Prev
    Next
    INDEX
    Explanations

    words before punctuation or list items

    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
    waite
    0.46
     gave
    0.45
     países
    0.45
    Е
    0.42
    -
    0.42
     tell
    0.42
     ,
    0.41
    /
    0.41
     and
    0.41
    Class
    0.41
    POSITIVE LOGITS
    dancer
    0.48
     പരിശോധ
    0.46
    钧
    0.46
    omorph
    0.45
     accessoires
    0.45
     konkre
    0.44
     donning
    0.44
    🕹
    0.43
     لتح
    0.43
     பக்தர்கள்
    0.43
    Activations Density 0.002%

    No Known Activations