© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11198
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and quantities

    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_40_width_16k_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
     second
    0.40
     하나
    0.38
     Secondly
    0.38
     Grand
    0.37
     четырех
    0.37
    四
    0.37
     three
    0.37
     Nun
    0.37
     Jak
    0.36
     mitad
    0.36
    POSITIVE LOGITS
     nth
    0.68
    第
    0.61
     kth
    0.58
     उतने
    0.55
     sebesar
    0.54
    nth
    0.53
     #${
    0.52
     n
    0.50
    ("["
    0.48
     कितने
    0.48
    Activations Density 0.290%

    No Known Activations