© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93349
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and terms

    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
     незавер
    -1.10
    ちなみに
    -1.09
     Fotograf
    -1.05
    Procedimento
    -1.05
    個人的には
    -1.04
     Abon
    -1.03
    厨师
    -0.97
     pidana
    -0.96
    ("}");
    -0.95
    ではまた
    -0.94
    POSITIVE LOGITS
     cálculos
    1.02
    thritis
    1.00
    隊
    0.97
     búsquedas
    0.96
     pasaron
    0.95
     möchtest
    0.93
     Obwohl
    0.93
     empuj
    0.91
     viendo
    0.90
    meability
    0.90
    Activations Density 0.071%

    No Known Activations