© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1112
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    er
    0.81
    र
    0.76
    en
    0.71
    ോധ
    0.68
    恫
    0.68
    erweise
    0.66
     severely
    0.66
     karş
    0.65
    ه
    0.65
    ни
    0.63
    POSITIVE LOGITS
     graders
    1.92
     century
    1.76
     baseman
    1.73
     grader
    1.51
     trimester
    1.47
     Century
    1.43
     முறையாக
    1.37
    century
    1.34
     instar
    1.33
     anniversary
    1.30
    Activations Density 0.182%

    No Known Activations