© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60587
    Prev
    Next
    INDEX
    Explanations

    Prime Minister

    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_10/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
     její
    -2.83
     umgangssprach
    -2.72
     übri
    -2.69
    ↵↵
    -2.67
    穽
    -2.56
     berühm
    -2.52
    
    -2.52
     nunmehr
    -2.48
     gewöhnlich
    -2.48
     stren
    -2.48
    POSITIVE LOGITS
    鲥
    3.09
     noël
    3.00
    Примеча
    2.92
    橚
    2.88
     multicolore
    2.81
    桖
    2.73
     ennemi
    2.72
    鄚
    2.70
     etek
    2.67
     kulak
    2.67
    Activations Density 0.007%

    No Known Activations