© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68617
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Junho
    -0.93
    ρέπει
    -0.87
     кам
    -0.85
     cả
    -0.81
     определить
    -0.80
    بعد
    -0.80
     BEFORE
    -0.79
    corso
    -0.79
    феры
    -0.79
     Economia
    -0.79
    POSITIVE LOGITS
     third
    1.20
     fifth
    1.19
     ninth
    1.18
     fourth
    1.16
     seventh
    1.00
     eighth
    0.97
     sixth
    0.97
     troisième
    0.93
     quatrième
    0.90
     cinquième
    0.82
    Activations Density 0.049%

    No Known Activations