© 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. 34-GEMMASCOPE-RES-131K
    7. 76315
    Prev
    Next
    INDEX
    Explanations

    Roman and Greek names ending in 'ius'

    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_34/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
    今では
    -0.88
     pescoço
    -0.82
    ついでに
    -0.81
    分かります
    -0.81
     solem
    -0.80
     Relig
    -0.80
     Chines
    -0.79
     affiliated
    -0.79
     Utili
    -0.77
    SceneManager
    -0.77
    POSITIVE LOGITS
     Effect
    0.93
     Effekt
    0.93
    ۳
    0.91
    getInstance
    0.89
    County
    0.88
    łat
    0.85
    Effect
    0.84
    вач
    0.83
     III
    0.83
     gibi
    0.81
    Activations Density 0.049%

    No Known Activations