© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11254
    Prev
    Next
    INDEX
    Explanations

    commas and separators

    np_acts-logits-general · gemini-2.5-flash-lite

    separators and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    financial
    0.45
     formations
    0.41
     financiar
    0.41
    帑
    0.41
    갚
    0.40
    assertEqual
    0.40
     =[
    0.39
    후
    0.39
    禿
    0.38
     финансо
    0.38
    POSITIVE LOGITS
     separator
    1.55
     separations
    1.45
     separation
    1.43
     Separ
    1.41
     separators
    1.41
     Separation
    1.38
     separating
    1.38
     comma
    1.36
    separator
    1.36
     separated
    1.35
    Activations Density 0.043%

    No Known Activations