© 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. 69928
    Prev
    Next
    INDEX
    Explanations

    current version version

    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
    ).
    -3.02
    籐
    -2.80
    lgari
    -2.48
    塤
    -2.41
            
    -2.41
     кнопки
    -2.34
     одном
    -2.31
    馴
    -2.30
    撓
    -2.27
     ponieważ
    -2.25
    POSITIVE LOGITS
    ’
    3.92
    
    3.00
    “
    3.00
    ed
    2.88
    、“
    2.55
    蕯
    2.53
    在自己
    2.52
    寕
    2.50
    薆
    2.48
     手绘
    2.45
    Activations Density 0.001%

    No Known Activations