© 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. 110734
    Prev
    Next
    INDEX
    Explanations

    serv, serviced, serveration

    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
     Möglichkeit
    -0.85
     Fähigkeit
    -0.81
     Pflichten
    -0.79
     organisé
    -0.78
     concerns
    -0.77
     dignidad
    -0.75
     conçu
    -0.75
     repor
    -0.74
     ave
    -0.73
     predicament
    -0.72
    POSITIVE LOGITS
     Serv
    1.42
    serv
    1.25
    Serv
    1.24
     servant
    1.15
     servants
    1.10
     SERV
    1.09
    illance
    1.09
    servable
    1.05
     serv
    1.03
    SERV
    1.03
    Activations Density 0.020%

    No Known Activations