© 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. 81402
    Prev
    Next
    INDEX
    Explanations

    Zuc / Zuli / Zuro / Zurn / Zuri / Zuk / Zun / Zuv

    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
    ünüz
    -0.78
    ouncy
    -0.70
     språk
    -0.69
    ensi
    -0.69
    },[])
    -0.69
     λε
    -0.68
    彰
    -0.68
    Parabéns
    -0.68
    Rm
    -0.67
     Frei
    -0.66
    POSITIVE LOGITS
    Zu
    0.93
    ЗУ
    0.83
     Зу
    0.81
    ftig
    0.80
     Zu
    0.79
    ኪ
    0.77
     theologian
    0.77
     Stol
    0.75
     recompense
    0.75
     adage
    0.74
    Activations Density 0.014%

    No Known Activations