© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71602
    Prev
    Next
    INDEX
    Explanations

    lifestyle

    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
     blaue
    -1.91
    踯
    -1.87
    訐
    -1.80
    鸸
    -1.77
    蟶
    -1.76
    ꦴ
    -1.75
    轫
    -1.73
    蟊
    -1.73
     variétés
    -1.72
     kleinere
    -1.68
    POSITIVE LOGITS
                
    2.03
                   
    1.80
    しました
    1.74
    .
    1.73
                 
    1.73
    if
    1.71
    宴会
    1.71
    数十
    1.71
     same
    1.68
     deine
    1.67
    Activations Density 0.016%

    No Known Activations